# Core.Today AI API — Image Generation Models

> Text-to-image and image-editing models (FLUX, Seedream, Imagen, nano-banana, GPT Image, ...) available through the Core.Today unified API.

Source: https://console.core.today/docs/image-models
This file: https://console.core.today/llms/image-models.txt
All models: https://console.core.today/llms.txt

## API Usage

Base URL: https://api.core.today/v1
Auth header: X-API-Key: YOUR_API_KEY

1. POST /predictions with {"model": "<model id>", "input": {...}} -> returns job_id
2. GET /predictions/{job_id} -> poll until status is "completed" or "failed"
3. result contains output URL(s); add "is_public": true for a permanent public URL

## Models (79)

### Background Remover — `851-labs/background-remover`

The most-used background remover on Replicate (27M+ runs). Removes backgrounds with soft alpha or hard segmentation, supports reverse mode (remove foreground), custom background types, and transparent PNG output — all at a very low price.

- Provider: 851 Labs
- Credits: 1 (per image)
- Speed: fast / Quality: high
- Required params: image (string)
- Optional params: threshold=0, reverse=false, background_type=rgba, format=png
- Example input:
```json
{
  "model": "851-labs/background-remover",
  "input": {
    "image": "https://example.com/product.jpg",
    "format": "png",
    "background_type": "rgba"
  }
}
```
- Full docs: https://console.core.today/docs/models/851-labs/background-remover

### BiRefNet — `men1scus/birefnet`

State-of-the-art open-source background removal. BiRefNet's high-fidelity dichotomous image segmentation delivers excellent edge quality on hair, fur, and fine details.

- Provider: BiRefNet
- Credits: 5 (per image)
- Speed: fast / Quality: ultra
- Required params: image (string)
- Optional params: resolution=
- Example input:
```json
{
  "model": "men1scus/birefnet",
  "input": {
    "image": "https://example.com/portrait.jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/men1scus/birefnet

### BLIP — `salesforce/blip`

Salesforce BLIP (173M+ runs) — image captioning, visual question answering, and image-text matching in one model. The classic choice for bulk captioning at 1 credit per image.

- Provider: Salesforce
- Credits: 1 (per image)
- Speed: fast / Quality: standard
- Required params: image (string)
- Optional params: task=image_captioning, question, caption
- Example input:
```json
{
  "model": "salesforce/blip",
  "input": {
    "image": "https://example.com/photo.jpg",
    "task": "image_captioning"
  }
}
```
- Full docs: https://console.core.today/docs/models/salesforce/blip

### Change Haircut — `flux-kontext-apps/change-haircut`

Change anyone's hairstyle and hair color from a single photo, powered by FLUX.1 Kontext [pro]. Choose from 90+ hairstyles and 30 hair colors — or let 'Random' surprise you — while keeping the face untouched.

- Provider: Black Forest Labs
- Credits: 93 (per image (fixed))
- Speed: fast / Quality: high
- Required params: input_image (string)
- Optional params: seed, gender=none, haircut=No change, hair_color=No change, aspect_ratio=match_input_image, output_format=png, safety_tolerance=2
- Example input:
```json
{
  "model": "flux-kontext-apps/change-haircut",
  "input": {
    "input_image": "https://example.com/portrait.png",
    "gender": "none",
    "haircut": "Random",
    "hair_color": "Random",
    "aspect_ratio": "match_input_image"
  }
}
```
- Full docs: https://console.core.today/docs/models/flux-kontext-apps/change-haircut

### Clarity Upscaler — `philz1337x/clarity-upscaler`

The famous creative upscaler (30M+ runs). Instead of just enlarging, it re-imagines detail while upscaling — with controllable creativity, resemblance, prompt guidance, and tiled diffusion for high scale factors.

- Provider: Clarity
- Credits: 60 (per generation)
- Speed: medium / Quality: ultra
- Required params: image (string)
- Optional params: prompt=masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>, negative_prompt=(worst quality, low quality, normal quality:2) JuggernautNegative-neg, scale_factor=2, dynamic=6, creativity=0.35, resemblance=0.6, tiling_width=112, tiling_height=144, sd_model=juggernaut_reborn.safetensors [338b85bc4f], scheduler=DPM++ 3M SDE Karras, num_inference_steps=18, seed=1337, downscaling=false, downscaling_resolution=768, lora_links=, custom_sd_model=, sharpen=0, mask, handfix=disabled, pattern=false, output_format=png
- Example input:
```json
{
  "model": "philz1337x/clarity-upscaler",
  "input": {
    "image": "https://example.com/ai-art.png",
    "scale_factor": 2,
    "creativity": 0.35,
    "resemblance": 0.6
  }
}
```
- Full docs: https://console.core.today/docs/models/philz1337x/clarity-upscaler

### CLIP Features — `andreasjansson/clip-features`

CLIP ViT-L/14 embeddings for text AND images (163M+ runs) — puts both in the same vector space for cross-modal search, image dedup, and zero-shot classification. 1 credit per run.

- Provider: CLIP
- Credits: 1 (per run (batch inputs with newlines))
- Speed: fast / Quality: high
- Optional params: inputs=a
b
- Example input:
```json
{
  "model": "andreasjansson/clip-features",
  "input": {
    "inputs": "a photo of a red sneaker\nhttps://example.com/sneaker.jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/andreasjansson/clip-features

### CodeFormer — `sczhou/codeformer`

Robust face restoration for old photos and AI-generated faces (54M+ runs). Its signature fidelity dial balances restoration quality against staying true to the original face, with Real-ESRGAN background enhancement built in.

- Provider: CodeFormer
- Credits: 8 (per image)
- Speed: fast / Quality: high
- Required params: image (string)
- Optional params: codeformer_fidelity=0.5, background_enhance=true, face_upsample=true, upscale=2
- Example input:
```json
{
  "model": "sczhou/codeformer",
  "input": {
    "image": "https://example.com/degraded-photo.jpg",
    "codeformer_fidelity": 0.7,
    "upscale": 2,
    "background_enhance": true,
    "face_upsample": true
  }
}
```
- Full docs: https://console.core.today/docs/models/sczhou/codeformer

### ControlNet Scribble — `jagilley/controlnet-scribble`

The classic sketch-to-image model (38M+ runs) — turn any scribble or line drawing into a detailed image guided by your prompt. Draw the composition, describe the content.

- Provider: ControlNet
- Credits: 120 (per run (num_samples '4' costs 480))
- Speed: medium / Quality: high
- Required params: prompt (string), image (string)
- Optional params: num_samples=1, image_resolution=512, ddim_steps=20, scale=9, seed, eta=0, a_prompt=best quality, extremely detailed, n_prompt=longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
- Example input:
```json
{
  "model": "jagilley/controlnet-scribble",
  "input": {
    "image": "https://example.com/house-sketch.png",
    "prompt": "a cozy cottage in a forest, warm sunset light, storybook illustration",
    "image_resolution": "512"
  }
}
```
- Full docs: https://console.core.today/docs/models/jagilley/controlnet-scribble

### Nano Banana (Edit) — `fal-ai/nano-banana/edit`

Dedicated edit endpoint for Nano Banana, Google's Gemini 2.5 Flash-based image model. Pass input image URLs to perform conversational editing with character consistency and multi-image fusion.

- Provider: Google
- Credits: 91 (per image)
- Speed: fast / Quality: high
- Required params: prompt (string), image_urls (array)
- Optional params: num_images=1, seed, aspect_ratio=auto, output_format=png, safety_tolerance=4, sync_mode=false, limit_generations=true
- Example input:
```json
{
  "model": "fal-ai/nano-banana/edit",
  "input": {
    "prompt": "Make the colors more vibrant and add a sunset glow",
    "image_urls": [
      "https://example.com/input-image.jpg"
    ],
    "aspect_ratio": "match_input_image",
    "output_format": "png",
    "safety_tolerance": "2",
    "num_images": 1
  }
}
```
- Full docs: https://console.core.today/docs/models/fal-ai/nano-banana/edit

### Nano Banana 2 (Edit) — `fal-ai/nano-banana-2/edit`

Edit endpoint for Nano Banana 2, built on Gemini 3.1 Flash Image. Adds resolution control (1K/2K/4K), Google Search grounding, and thinking mode while preserving conversational editing and multi-image fusion.

- Provider: Google
- Credits: 190 (per image (1K); 280 for 2K, 370 for 4K)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: num_images=1, seed, aspect_ratio=auto, output_format=png, safety_tolerance=4, sync_mode=false, image_urls, system_prompt=, resolution=1K, video_url, audio_url, pdf_url, limit_generations=true, enable_web_search=false, thinking_level
- Example input:
```json
{
  "model": "fal-ai/nano-banana-2/edit",
  "input": {
    "prompt": "make a photo of the man driving the car down the california coastline",
    "image_urls": [
      "https://storage.googleapis.com/falserverless/example_inputs/nano-banana-edit-input.png",
      "https://storage.googleapis.com/falserverless/example_inputs/nano-banana-edit-input-2.png"
    ],
    "aspect_ratio": "auto",
    "resolution": "1K",
    "output_format": "png",
    "num_images": 1
  }
}
```
- Full docs: https://console.core.today/docs/models/fal-ai/nano-banana-2/edit

### Nano Banana Pro (Edit) — `fal-ai/nano-banana-pro/edit`

Edit endpoint for Nano Banana Pro built on Gemini 3 Pro. Professional-grade controls, legible multilingual typography, real-time grounding via Google Search, and resolution up to 2K for editing.

- Provider: Google
- Credits: 350 (per image (1K); 700 for 2K)
- Speed: medium / Quality: ultra
- Required params: prompt (string), image_urls (array)
- Optional params: num_images=1, seed, aspect_ratio=auto, output_format=png, safety_tolerance=4, sync_mode=false, system_prompt=, resolution=1K, limit_generations=true, enable_web_search=false
- Example input:
```json
{
  "model": "fal-ai/nano-banana-pro/edit",
  "input": {
    "prompt": "Make the colors more vibrant and add a sunset glow",
    "image_urls": [
      "https://example.com/input-image.jpg"
    ],
    "aspect_ratio": "match_input_image",
    "resolution": "1K",
    "output_format": "png",
    "num_images": 1
  }
}
```
- Full docs: https://console.core.today/docs/models/fal-ai/nano-banana-pro/edit

### Face to Many — `fofr/face-to-many`

Turn a face photo into 6 fun styles (15M+ runs) — 3D, Emoji, Video game, Pixels, Clay, or Toy. The viral avatar generator behind countless profile-picture apps.

- Provider: fofr
- Credits: 21 (per generation)
- Speed: fast / Quality: high
- Optional params: prompt=a person, image, style=3D, negative_prompt=, denoising_strength=0.65, prompt_strength=4.5, control_depth_strength=0.8, instant_id_strength=1, seed, custom_lora_url, lora_scale=1
- Example input:
```json
{
  "model": "fofr/face-to-many",
  "input": {
    "image": "https://example.com/selfie.jpg",
    "style": "Emoji"
  }
}
```
- Full docs: https://console.core.today/docs/models/fofr/face-to-many

### Face to Sticker — `fofr/face-to-sticker`

Turn any face photo into a fun die-cut sticker (1.6M+ runs). InstantID keeps the likeness while IP-Adapter controls take the artwork from faithful caricature to loose cartoon — with an optional 2x upscale for print quality.

- Provider: fofr
- Credits: 22 (per run (43 credits when upscale is true))
- Speed: fast / Quality: high
- Optional params: prompt=a person, image, negative_prompt=, width=1024, height=1024, steps=20, seed, prompt_strength=7, instant_id_strength=1, ip_adapter_weight=0.2, ip_adapter_noise=0.5, upscale=false, upscale_steps=10
- Example input:
```json
{
  "model": "fofr/face-to-sticker",
  "input": {
    "image": "https://example.com/face.webp",
    "prompt": "arnold",
    "prompt_strength": 4.5,
    "instant_id_strength": 0.7,
    "ip_adapter_weight": 0.2,
    "upscale": false
  }
}
```
- Full docs: https://console.core.today/docs/models/fofr/face-to-sticker

### Florence-2 Large — `lucataco/florence-2-large`

Microsoft's Florence-2 all-in-one vision model — captioning, object detection, phrase grounding, OCR, and segmentation in a single API. Pick a task, optionally add text input, done.

- Provider: Microsoft
- Credits: 2 (per call)
- Speed: fast / Quality: high
- Required params: image (string)
- Optional params: task_input=Caption, text_input
- Example input:
```json
{
  "model": "lucataco/florence-2-large",
  "input": {
    "image": "https://example.com/document.jpg",
    "task_input": "OCR with Region"
  }
}
```
- Full docs: https://console.core.today/docs/models/lucataco/florence-2-large

### FLUX.2 Klein 4B — `black-forest-labs/flux-2-klein-4b`

Very fast image generation and editing model. 4-step distilled, sub-second inference for production and near real-time applications.

- Provider: Black Forest Labs
- Credits: 2 (per image at 1MP (default); 2 credits at 0.25-0.5MP, 4 at 2MP, 8 at 4MP)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: images=[], aspect_ratio=1:1, output_megapixels=1, seed, go_fast=false, output_format=jpg, output_quality=95, disable_safety_checker=false
- Example input:
```json
{
  "model": "black-forest-labs/flux-2-klein-4b",
  "input": {
    "prompt": "A surreal underwater or cosmic garden scene with bioluminescent flora against a deep navy background",
    "output_megapixels": "1",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-2-klein-4b

### FLUX 2 Flex — `black-forest-labs/flux-2-flex`

Maximum-quality FLUX model supporting up to 10 reference images and advanced typography. The most capable model for complex, multi-reference creative projects.

- Provider: Black Forest Labs
- Credits: 280 (per image)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: input_images=[], aspect_ratio=1:1, resolution=1 MP, width, height, safety_tolerance=2, seed, prompt_upsampling=true, steps=30, guidance=4.5, output_format=webp, output_quality=80
- Example input:
```json
{
  "model": "black-forest-labs/flux-2-flex",
  "input": {
    "prompt": "Premium brand campaign visual combining modern architecture with natural elements, luxury lifestyle aesthetic, professional advertising quality, 8k",
    "image_size": "landscape_16_9",
    "num_inference_steps": 50,
    "guidance_scale": 3.5
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-2-flex

### FLUX 2 Max — `black-forest-labs/flux-2-max`

The highest fidelity image model from Black Forest Labs. Best-in-class prompt following and the most consistent editing in the FLUX.2 lineup — preserves colors, lighting, faces, text, and objects across edits with up to 8 reference images.

- Provider: Black Forest Labs
- Credits: 160 (per image at 1 MP — varies by resolution (0.5MP 130, 2MP 230, 4MP/match_input 370, custom 390))
- Speed: fast / Quality: ultra
- Required params: prompt (string)
- Optional params: input_images=[], aspect_ratio=1:1, resolution=1 MP, width, height, safety_tolerance=2, seed, output_format=webp, output_quality=80
- Example input:
```json
{
  "model": "black-forest-labs/flux-2-max",
  "input": {
    "prompt": "A photorealistic wide shot of a minimalist digital billboard in a forest of purple and lavender-hued trees. Centered text reads \"FLUX.2 [max]\" in a modern sans-serif font. Soft daylight with a purple color cast, cinematic composition",
    "resolution": "1 MP",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-2-max

### FLUX 2 Pro — `black-forest-labs/flux-2-pro`

Professional-grade FLUX 2 with high-quality editing and up to 8 reference image support. Excellent balance of quality, speed, and creative control.

- Provider: Black Forest Labs
- Credits: 70 (per image)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: input_images=[], aspect_ratio=1:1, resolution=1 MP, width, height, safety_tolerance=2, seed, output_format=webp, output_quality=80
- Example input:
```json
{
  "model": "black-forest-labs/flux-2-pro",
  "input": {
    "prompt": "Luxury perfume bottle on polished marble surface, soft diffused lighting, editorial advertisement quality, shallow depth of field, 8k ultra detailed",
    "image_size": "square_hd",
    "guidance_scale": 3.5
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-2-pro

### FLUX.2 Dev — `black-forest-labs/flux-2-dev`

Development version of FLUX.2 with image editing capabilities and reference image support. Ideal for iterative design workflows and experimentation.

- Provider: Black Forest Labs
- Credits: 28 (per image)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: input_images=[], go_fast=true, aspect_ratio=1:1, width, height, seed, output_format=webp, output_quality=80, disable_safety_checker=false
- Example input:
```json
{
  "model": "black-forest-labs/flux-2-dev",
  "input": {
    "prompt": "A cozy reading nook with warm lighting, vintage armchair, floor-to-ceiling bookshelves, photorealistic interior design",
    "image_size": "landscape_4_3",
    "num_inference_steps": 28,
    "guidance_scale": 3.5
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-2-dev

### FLUX 1.1 Pro — `black-forest-labs/flux-1.1-pro`

Fast high-quality image generation, an upgrade to FLUX.1 Pro with faster speed and improved quality. Perfect for production workloads requiring both speed and fidelity.

- Provider: Black Forest Labs
- Credits: 93 (per image)
- Speed: fast / Quality: ultra
- Required params: prompt (string)
- Optional params: seed, width, height, aspect_ratio=1:1, image_prompt, output_format=webp, output_quality=80, safety_tolerance=2, prompt_upsampling=false
- Example input:
```json
{
  "model": "black-forest-labs/flux-1.1-pro",
  "input": {
    "prompt": "Cinematic portrait of a woman in golden hour light, shallow depth of field, film grain, professional photography, 8k ultra detailed",
    "image_size": "portrait_4_3"
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-1.1-pro

### FLUX 1.1 Pro Ultra — `black-forest-labs/flux-1.1-pro-ultra`

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels — the highest-resolution tier of the FLUX 1.1 Pro family. Use raw mode for realism.

- Provider: Black Forest Labs
- Credits: 140 (per image)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: raw=false, image_prompt, image_prompt_strength=0.1, aspect_ratio=1:1, safety_tolerance=2, output_format=jpg, seed
- Example input:
```json
{
  "model": "black-forest-labs/flux-1.1-pro-ultra",
  "input": {
    "prompt": "a majestic snow-capped mountain peak bathed in a warm glow of the setting sun",
    "aspect_ratio": "3:2",
    "raw": false
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-1.1-pro-ultra

### FLUX Dev — `black-forest-labs/flux-dev`

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions, tuned for open, high-quality experimentation.

- Provider: Black Forest Labs
- Credits: 58 (per call (flat, regardless of num_outputs 1-4))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, image, prompt_strength=0.8, num_outputs=1, num_inference_steps=28, guidance=3, seed, output_format=webp, output_quality=80, disable_safety_checker=false, go_fast=true, megapixels=1
- Example input:
```json
{
  "model": "black-forest-labs/flux-dev",
  "input": {
    "prompt": "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
    "aspect_ratio": "1:1",
    "go_fast": true
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-dev

### FLUX Kontext Max — `black-forest-labs/flux-kontext-max`

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts.

- Provider: Black Forest Labs
- Credits: 190 (per image)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: input_image, aspect_ratio=match_input_image, output_format=png, safety_tolerance=2, prompt_upsampling=false, seed
- Example input:
```json
{
  "model": "black-forest-labs/flux-kontext-max",
  "input": {
    "prompt": "Make the letters 3D, floating in space on a city street",
    "input_image": "https://replicate.delivery/xezq/XfwWjHJ7HfrmXE6ukuLVEpXWfeQ3PQeRI5mApuLXRxST7XMmC/tmpc91tlq20.png",
    "aspect_ratio": "match_input_image"
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-kontext-max

### FLUX Kontext Pro — `black-forest-labs/flux-kontext-pro`

State-of-the-art text-based image editing model that transforms images through natural language. Excellent for style transfer, object modification, text replacement, background changes, and character consistency.

- Provider: Black Forest Labs
- Credits: 93 (per image)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: input_image, aspect_ratio=match_input_image, output_format=png, safety_tolerance=2, prompt_upsampling=false, seed
- Example input:
```json
{
  "model": "black-forest-labs/flux-kontext-pro",
  "input": {
    "prompt": "Make this a 90s cartoon",
    "input_image": "https://replicate.delivery/pbxt/N55l5TWGh8mSlNzW8usReoaNhGbFwvLeZR3TX1NL4pd2Wtfv/replicate-prediction-f2d25rg6gnrma0cq257vdw2n4c.png",
    "aspect_ratio": "match_input_image",
    "output_format": "jpg",
    "safety_tolerance": 2
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-kontext-pro

### FLUX.1 Krea [dev] — `black-forest-labs/flux-krea-dev`

Photorealistic image generation that specifically avoids the 'AI look', producing natural-looking images indistinguishable from real photographs.

- Provider: Krea AI
- Credits: 58 (per image)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, image, prompt_strength=0.8, num_outputs=1, num_inference_steps=28, guidance=3, seed, output_format=webp, output_quality=80, disable_safety_checker=false, go_fast=true, megapixels=1
- Example input:
```json
{
  "model": "black-forest-labs/flux-krea-dev",
  "input": {
    "prompt": "Candid photograph of a barista making latte art in a cozy coffee shop, natural window lighting, shot on Canon EOS R5, shallow depth of field",
    "image_size": "portrait_4_3",
    "num_inference_steps": 28,
    "guidance_scale": 3.5
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-krea-dev

### FLUX PuLID — `bytedance/flux-pulid`

PuLID identity customization on FLUX-dev: generate photorealistic portraits of a specific person from one face photo, with markedly higher fidelity than SDXL-based variants. Tune id_weight and start_step to balance likeness against prompt editability.

- Provider: ByteDance
- Credits: 47 (46 credits x num_outputs (1-4 images))
- Speed: medium / Quality: high
- Required params: main_face_image (string)
- Optional params: prompt=portrait, color, cinematic, negative_prompt=bad quality, worst quality, text, signature, watermark, extra limbs, low resolution, partially rendered objects, deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed, blurry, width=896, height=1152, num_steps=20, start_step=0, guidance_scale=4, id_weight=1, seed, true_cfg=1, max_sequence_length=128, output_format=webp, output_quality=80, num_outputs=1
- Example input:
```json
{
  "model": "bytedance/flux-pulid",
  "input": {
    "main_face_image": "https://example.com/woman.png",
    "prompt": "a woman holding sign with glowing green text \"PuLID for FLUX\"",
    "width": 896,
    "height": 1152,
    "start_step": 4,
    "num_outputs": 4
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/flux-pulid

### FLUX.1 Schnell — `black-forest-labs/flux-schnell`

Ultra-fast image generation model optimized for speed. Generates high-quality images in just 1-2 seconds, perfect for real-time applications and rapid prototyping.

- Provider: Black Forest Labs
- Credits: 7 (per image)
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, num_outputs=1, num_inference_steps=4, seed, output_format=webp, output_quality=80, disable_safety_checker=false, go_fast=true, megapixels=1
- Example input:
```json
{
  "model": "black-forest-labs/flux-schnell",
  "input": {
    "prompt": "A sleek wireless headphone on a minimalist white marble surface, professional product photography, soft studio lighting, 8k ultra detailed",
    "image_size": "landscape_4_3",
    "num_inference_steps": 4
  }
}
```
- Full docs: https://console.core.today/docs/models/black-forest-labs/flux-schnell

### Runway Gen-4 Image — `runwayml/gen4-image`

Runway's Gen-4 Image model with references: combine up to 3 reference images with @tag mentions in your prompt to keep characters, objects, and locations consistent across every angle and scene, at 720p or 1080p.

- Provider: Runway
- Credits: 190 (per image at 1080p (default) — 720p 120 credits, 1080p 190 credits)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: seed, resolution=1080p, aspect_ratio=16:9, reference_tags=[], reference_images=[]
- Example input:
```json
{
  "model": "runwayml/gen4-image",
  "input": {
    "prompt": "a close up portrait of @woman and @man standing in @park, hands in pockets, looking cool. She is wearing her pink sweater and bangles.",
    "resolution": "1080p",
    "aspect_ratio": "4:3",
    "reference_tags": [
      "park",
      "woman",
      "man"
    ],
    "reference_images": [
      "https://example.com/park.jpg",
      "https://example.com/woman.jpg",
      "https://example.com/man.jpg"
    ]
  }
}
```
- Full docs: https://console.core.today/docs/models/runwayml/gen4-image

### Runway Gen-4 Image Turbo — `runwayml/gen4-image-turbo`

Gen-4 Image Turbo is 2.5x faster and cheaper than Gen-4 Image, with the same reference-driven API: use 1 to 3 reference images with @tag mentions for consistent characters and objects, at a flat price regardless of resolution.

- Provider: Runway
- Credits: 70 (per image — flat rate regardless of resolution (720p/1080p))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: seed, resolution=1080p, aspect_ratio=16:9, reference_tags=[], reference_images=[]
- Example input:
```json
{
  "model": "runwayml/gen4-image-turbo",
  "input": {
    "prompt": "a close up portrait of @woman and @man driving fast in a red 1980s sports car",
    "resolution": "1080p",
    "aspect_ratio": "4:3",
    "reference_tags": [
      "woman",
      "man"
    ],
    "reference_images": [
      "https://example.com/woman.jpg",
      "https://example.com/man.jpg"
    ]
  }
}
```
- Full docs: https://console.core.today/docs/models/runwayml/gen4-image-turbo

### GFPGAN — `tencentarc/gfpgan`

Tencent ARC's face restoration model — 115M+ runs, the most-run model in the restoration collection. Restores old/blurry photos and fixes faces in AI-generated images.

- Provider: Tencent ARC
- Credits: 6 (per image)
- Speed: fast / Quality: high
- Required params: img (string)
- Optional params: version=v1.4, scale=2
- Example input:
```json
{
  "model": "tencentarc/gfpgan",
  "input": {
    "img": "https://example.com/old-photo.jpg",
    "version": "v1.4",
    "scale": 2
  }
}
```
- Full docs: https://console.core.today/docs/models/tencentarc/gfpgan

### GPT Image 2 — `openai/gpt-image-2`

OpenAI's state-of-the-art image generation and editing model with strong instruction following, sharp text rendering, and detailed editing. Quality-based pricing lets you trade off cost vs. fidelity.

- Provider: OpenAI
- Credits: 300 (per image (high/auto); 110 for medium, 29 for low)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: openai_api_key, aspect_ratio=1:1, input_images, number_of_images=1, quality=auto, background=auto, output_compression=90, output_format=webp, moderation=auto, user_id
- Example input:
```json
{
  "model": "openai/gpt-image-2",
  "input": {
    "prompt": "A photorealistic close-up portrait of an elderly Japanese ceramicist with deep wrinkles and a warm smile, carefully inspecting a freshly glazed tea bowl in his rustic sun-drenched workshop.",
    "aspect_ratio": "3:2",
    "quality": "high",
    "output_format": "webp"
  }
}
```
- Full docs: https://console.core.today/docs/models/openai/gpt-image-2

### GPT Image 1.5 — `openai/gpt-image-1.5`

OpenAI's latest image generation model with better instruction following and adherence to prompts, including sharp text rendering and detailed editing.

- Provider: OpenAI
- Credits: 310 (per image at high/auto quality; 31 at low, 120 at medium)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: openai_api_key, aspect_ratio=1:1, input_fidelity=low, input_images, number_of_images=1, quality=auto, background=auto, output_compression=90, output_format=webp, moderation=auto, user_id
- Example input:
```json
{
  "model": "openai/gpt-image-1.5",
  "input": {
    "prompt": "make a scene in chelsea, london in the 1970s, photorealistic, everything in focus, with tons of people, and a bus with an advertisement for \"ImageGen 1.5 on Replicate\"",
    "quality": "high",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/openai/gpt-image-1.5

### Grok Imagine Image — `xai/grok-imagine-image`

Generate images using xAI's Grok Imagine model. Sibling to Grok Imagine Video, sharing the same underlying Grok Imagine architecture for fast text-to-image generation.

- Provider: xAI
- Credits: 47 (per image)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: image, aspect_ratio=1:1
- Example input:
```json
{
  "model": "xai/grok-imagine-image",
  "input": {
    "prompt": "A futuristic city skyline at sunset, flying vehicles, neon reflections on glass towers",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/xai/grok-imagine-image

### Grounding DINO — `adirik/grounding-dino`

Text-prompted object detection (39M+ runs) — describe what to find in natural language ('red car, person wearing a hat') and get bounding boxes with confidence scores plus an annotated image.

- Provider: Grounding DINO
- Credits: 2 (per image)
- Speed: fast / Quality: high
- Optional params: image, query, box_threshold=0.25, text_threshold=0.25, show_visualisation=true
- Example input:
```json
{
  "model": "adirik/grounding-dino",
  "input": {
    "image": "https://example.com/shelf.jpg",
    "query": "soda can, water bottle, snack bag",
    "box_threshold": 0.3
  }
}
```
- Full docs: https://console.core.today/docs/models/adirik/grounding-dino

### Hunyuan 3D 3.1 — `tencent/hunyuan-3d-3.1`

Tencent's flagship 3D generation — create high-polygon textured 3D models from a text prompt OR an image, with optional PBR (physically based rendering) materials.

- Provider: Tencent
- Credits: 1160 (per generation)
- Speed: slow / Quality: ultra
- Optional params: prompt, image, enable_pbr=false, face_count=500000, generate_type=Normal
- Example input:
```json
{
  "model": "tencent/hunyuan-3d-3.1",
  "input": {
    "prompt": "A cute low-poly cartoon fox sitting, game asset style",
    "generate_type": "Normal",
    "enable_pbr": true
  }
}
```
- Full docs: https://console.core.today/docs/models/tencent/hunyuan-3d-3.1

### Ideogram V4 Balanced — `ideogram-ai/ideogram-v4-balanced`

A middle-ground tier in Ideogram's v4 family, balancing generation speed and output quality. Delivers strong typography and photorealism at a lower cost than the Quality tier.

- Provider: Ideogram
- Credits: 140 (per image (fixed price))
- Speed: medium / Quality: high
- Optional params: prompt, json_prompt, resolution=None, enable_copyright_detection=false
- Example input:
```json
{
  "model": "ideogram-ai/ideogram-v4-balanced",
  "input": {
    "prompt": "A bright Instagram promo graphic for a summer sale with the headline \"UP TO 40% OFF\" in bold rounded typography, tropical leaf pattern background in coral and teal",
    "resolution": "2048x2048"
  }
}
```
- Full docs: https://console.core.today/docs/models/ideogram-ai/ideogram-v4-balanced

### Ideogram V4 Quality — `ideogram-ai/ideogram-v4-quality`

The highest-fidelity tier of Ideogram's v4 model family, tuned for maximum detail, realism, and typography accuracy. Best suited for final production assets where quality matters more than speed.

- Provider: Ideogram
- Credits: 230 (per image (fixed price))
- Speed: slow / Quality: ultra
- Optional params: prompt, json_prompt, resolution=None, enable_copyright_detection=false
- Example input:
```json
{
  "model": "ideogram-ai/ideogram-v4-quality",
  "input": {
    "prompt": "A minimalist logo for a specialty coffee roastery called \"ATLAS ROASTING CO.\", bold sans-serif wordmark in deep charcoal, small mountain peak icon above the text, clean white background",
    "resolution": "2048x2048"
  }
}
```
- Full docs: https://console.core.today/docs/models/ideogram-ai/ideogram-v4-quality

### Ideogram V4 Turbo — `ideogram-ai/ideogram-v4-turbo`

The fastest and cheapest model in Ideogram's v4 family, built for rapid iteration while retaining Ideogram's signature text rendering and style consistency.

- Provider: Ideogram
- Credits: 70 (per image (fixed price))
- Speed: fast / Quality: standard
- Optional params: prompt, json_prompt, resolution=None, enable_copyright_detection=false
- Example input:
```json
{
  "model": "ideogram-ai/ideogram-v4-turbo",
  "input": {
    "prompt": "A bold event flyer with the headline \"SUMMER BEATS FESTIVAL\" in graffiti-style lettering, neon pink and electric blue color scheme, silhouettes of a crowd at the bottom"
  }
}
```
- Full docs: https://console.core.today/docs/models/ideogram-ai/ideogram-v4-turbo

### Ideogram V3 Turbo — `ideogram-ai/ideogram-v3-turbo`

The fastest and cheapest Ideogram v3 tier. V3 creates images with stunning realism, creative designs, and consistent styles.

- Provider: Ideogram
- Credits: 70 (per image)
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, resolution=None, magic_prompt_option=Auto, image, mask, style_type=None, style_reference_images, seed, style_preset=None
- Example input:
```json
{
  "model": "ideogram-ai/ideogram-v3-turbo",
  "input": {
    "prompt": "The text \"V3 Turbo\" in the center middle. A color film-inspired portrait of a young man looking to the side with a shallow depth of field.",
    "aspect_ratio": "3:2",
    "magic_prompt_option": "Auto"
  }
}
```
- Full docs: https://console.core.today/docs/models/ideogram-ai/ideogram-v3-turbo

### Ideogram Character — `ideogram-ai/ideogram-character`

Generate consistent characters from a single reference image. Render the same character in many styles — realistic or fiction — insert them into existing photos with mask inpainting, and rely on Ideogram's signature text rendering for legible signs and typography.

- Provider: Ideogram
- Credits: 350 (per image at Default rendering — Turbo 230, Default 350, Quality 470 credits)
- Speed: medium / Quality: ultra
- Required params: prompt (string), character_reference_image (string)
- Optional params: mask, seed, image, resolution=None, style_type=Auto, aspect_ratio=1:1, rendering_speed=Default, magic_prompt_option=Auto
- Example input:
```json
{
  "model": "ideogram-ai/ideogram-character",
  "input": {
    "prompt": "a close up photo of a woman in a fashion magazine photoshoot",
    "resolution": "None",
    "style_type": "Auto",
    "aspect_ratio": "1:1",
    "magic_prompt_option": "Auto",
    "character_reference_image": "https://example.com/character.webp"
  }
}
```
- Full docs: https://console.core.today/docs/models/ideogram-ai/ideogram-character

### MiniMax Image-01 — `minimax/image-01`

MiniMax's first image generation model with character reference support: provide a single face photo via subject_reference and generate consistent images of that person across prompts, styles, and aspect ratios — up to 9 images per request.

- Provider: MiniMax
- Credits: 23 (per image — 23 credits × number_of_images (1-9))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: subject_reference, aspect_ratio=1:1, number_of_images=1, prompt_optimizer=true
- Example input:
```json
{
  "model": "minimax/image-01",
  "input": {
    "prompt": "A close-up portrait of a leopard with distinctive spotted pattern and intense eyes",
    "aspect_ratio": "3:4",
    "number_of_images": 1,
    "prompt_optimizer": true
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/image-01

### Topaz Image Upscale — `topazlabs/image-upscale`

Professional-grade upscaling from Topaz Labs, the industry standard for photo enhancement. Five specialized enhance models, up to 6x upscale, subject detection, and optional face enhancement.

- Provider: Topaz Labs
- Credits: 190 (per image)
- Speed: medium / Quality: ultra
- Required params: image (string)
- Optional params: enhance_model=Standard V2, upscale_factor=None, output_format=jpg, subject_detection=None, face_enhancement=false, face_enhancement_creativity=0, face_enhancement_strength=0.8
- Example input:
```json
{
  "model": "topazlabs/image-upscale",
  "input": {
    "image": "https://example.com/photo.jpg",
    "enhance_model": "High Fidelity V2",
    "upscale_factor": "4x",
    "face_enhancement": true
  }
}
```
- Full docs: https://console.core.today/docs/models/topazlabs/image-upscale

### Imagen 4 — `google/imagen-4`

Google's Imagen 4 flagship text-to-image model.

- Provider: Google
- Credits: 93 (per image (flat, regardless of 1K/2K image_size))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, image_size=1K, safety_filter_level=block_only_high, output_format=jpg
- Example input:
```json
{
  "model": "google/imagen-4",
  "input": {
    "prompt": "The photo: Create a cinematic, photorealistic medium shot capturing the nostalgic warmth of a late 90s indie film.",
    "aspect_ratio": "16:9",
    "safety_filter_level": "block_medium_and_above"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/imagen-4

### Imagen 4 Fast — `google/imagen-4-fast`

A fast version of Imagen 4 for when speed and cost are more important than maximum quality.

- Provider: Google
- Credits: 46 (per image)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, safety_filter_level=block_only_high, output_format=jpg
- Example input:
```json
{
  "model": "google/imagen-4-fast",
  "input": {
    "prompt": "The photo: Create a cinematic, photorealistic medium shot capturing the dynamic energy of a high-octane action film.",
    "aspect_ratio": "4:3",
    "output_format": "jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/imagen-4-fast

### Bria Increase Resolution — `bria/increase-resolution`

Bria's commercially-safe image upscaler (130K+ runs). Increase resolution 2x or 4x with a model trained exclusively on licensed data, preserving alpha transparency — built for enterprise pipelines that require full legal liability coverage.

- Provider: Bria
- Credits: 93 (per image (x2 and x4 same price))
- Speed: fast / Quality: high
- Optional params: image, image_url, desired_increase=2, preserve_alpha=true, sync=true, content_moderation=false
- Example input:
```json
{
  "model": "bria/increase-resolution",
  "input": {
    "image": "https://example.com/logo.png",
    "desired_increase": 4,
    "preserve_alpha": true
  }
}
```
- Full docs: https://console.core.today/docs/models/bria/increase-resolution

### Krea 2 Large — `krea/krea-2-large`

Krea AI's flagship text-to-image model, focused on photorealistic output with strong prompt adherence. Supports style-reference and moodboard-guided generation for consistent visual direction.

- Provider: Krea AI
- Credits: 140 (per image (fixed price))
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, creativity=medium, style_reference_images=[], style_reference_strength=0.5, moodboard_id, moodboard_strength=0.35, seed
- Example input:
```json
{
  "model": "krea/krea-2-large",
  "input": {
    "prompt": "A photorealistic studio shot of a matte black ceramic coffee mug on a warm oak wood table, soft natural window light from the left, shallow depth of field",
    "aspect_ratio": "4:3",
    "creativity": "low"
  }
}
```
- Full docs: https://console.core.today/docs/models/krea/krea-2-large

### Krea 2 Medium — `krea/krea-2-medium`

A lower-cost variant of Krea 2 Large, trading some fidelity for faster and cheaper generation while keeping the same photorealistic style focus.

- Provider: Krea AI
- Credits: 70 (per image)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: aspect_ratio=1:1, creativity=medium, style_reference_images=[], style_reference_strength=0.5, moodboard_id, moodboard_strength=0.35, seed
- Example input:
```json
{
  "model": "krea/krea-2-medium",
  "input": {
    "prompt": "A ceramic coffee mug on a wooden table near a window, soft morning light, shallow depth of field",
    "aspect_ratio": "4:3",
    "creativity": "medium"
  }
}
```
- Full docs: https://console.core.today/docs/models/krea/krea-2-medium

### Microsoft MAI-Image 2.5 Pro — `microsoft/mai-image-2.5-pro`

Microsoft's highest-fidelity image model for production-grade text-to-image generation via Fal.AI. Built for hero imagery, detailed compositions, precise text rendering, photorealism, stylized illustration, commercial design, and visually rich concept work.

- Provider: Microsoft
- Credits: 400 (per image)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: num_images=1, aspect_ratio=auto, output_format=png, sync_mode=false
- Example input:
```json
{
  "model": "microsoft/mai-image-2.5-pro",
  "input": {
    "prompt": "A photorealistic concept-art poster of a university campus at sunset, cinematic lighting, a banner reading \"LOUISVILLE\" in bold serif type.",
    "aspect_ratio": "auto",
    "output_format": "png",
    "num_images": 1
  }
}
```
- Full docs: https://console.core.today/docs/models/microsoft/mai-image-2.5-pro

### Moondream2 — `lucataco/moondream2`

Small but capable vision-language model (14M+ runs) — ask free-form questions about any image and get detailed answers. Efficient VQA for tagging, moderation prep, and rich alt-text.

- Provider: Moondream
- Credits: 5 (per image)
- Speed: fast / Quality: high
- Required params: image (string)
- Optional params: prompt=Describe this image
- Example input:
```json
{
  "model": "lucataco/moondream2",
  "input": {
    "image": "https://example.com/scene.jpg",
    "prompt": "Describe this image in detail, including colors, objects, and mood."
  }
}
```
- Full docs: https://console.core.today/docs/models/lucataco/moondream2

### Multilingual E5 Large — `beautyyuyanli/multilingual-e5-large`

Multilingual text embeddings (74M+ runs) — 1024-dimension vectors across 100 languages including Korean. Pairs perfectly with Core.Today customer databases' vector search (knn_vector).

- Provider: E5
- Credits: 2 (per run (batch multiple texts in one call))
- Speed: fast / Quality: high
- Optional params: texts=["In the water, fish are swimming.", "Fish swim in the water.", "A book lies open on the table."], batch_size=32, normalize_embeddings=true
- Example input:
```json
{
  "model": "beautyyuyanli/multilingual-e5-large",
  "input": {
    "texts": "[\"코어닷투데이는 AI API 게이트웨이입니다.\", \"크레딧 기반 과금을 지원합니다.\"]",
    "normalize_embeddings": true
  }
}
```
- Full docs: https://console.core.today/docs/models/beautyyuyanli/multilingual-e5-large

### Nano Banana 2 (Gemini 3.1 Flash Image) — `google/nano-banana-2`

Google's fast image generation model built on Gemini 3.1 Flash Image. The high-efficiency counterpart to Nano Banana Pro — combining Pro-level visual quality with Flash-level speed and pricing. Features conversational editing, multi-image fusion, character consistency, accurate text rendering, and Google Search grounding. Supports up to 14 reference images and resolutions up to 4K.

- Provider: Google
- Credits: 190 (per image (1K), 280 for 2K, 370 for 4K)
- Speed: fast / Quality: ultra
- Required params: prompt (string)
- Optional params: image_input=[], aspect_ratio=match_input_image, resolution=1K, google_search=false, image_search=false, output_format=jpg
- Example input:
```json
{
  "model": "google/nano-banana-2",
  "input": {
    "prompt": "A photorealistic close-up portrait of an elderly Japanese ceramicist with deep wrinkles and a warm smile, carefully inspecting a freshly glazed tea bowl in his rustic sun-drenched workshop.",
    "aspect_ratio": "3:4",
    "resolution": "2K",
    "output_format": "jpeg"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/nano-banana-2

### Nano Banana 2 Lite — `google/nano-banana-2-lite`

Google's lightweight Nano Banana 2 variant built on Gemini 3.1 Flash Image, tuned for faster and cheaper generation. Retains conversational editing, multi-image fusion, and character consistency from the full Nano Banana 2.

- Provider: Google
- Credits: 80 (per image (fixed price))
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: image_input=[], aspect_ratio=match_input_image, output_format=jpg
- Example input:
```json
{
  "model": "google/nano-banana-2-lite",
  "input": {
    "prompt": "Change the background to a warm sunset gradient and add soft rim lighting on the product",
    "image_input": [
      "https://example.com/product-photo.jpg"
    ],
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/nano-banana-2-lite

### Nano Banana — `google/nano-banana`

Google Gemini 2.5 Flash-based image generation with multimodal editing capabilities. Fast and versatile for both creation and editing tasks.

- Provider: Google
- Credits: 91 (per image)
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: image_input=[], aspect_ratio=match_input_image, output_format=jpg
- Example input:
```json
{
  "model": "google/nano-banana",
  "input": {
    "prompt": "Whimsical illustration of a cat astronaut floating in space with planets and stars, colorful and playful style",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/nano-banana

### Nano Banana Pro (Gemini 3 Pro Image) — `google/nano-banana-pro`

Google's state-of-the-art image generation and editing model built on Gemini 3 Pro. Creates detailed visuals with legible text in multiple languages, connects to real-time information from Google Search, and provides professional-grade creative controls. Supports up to 14 reference images and resolutions up to 4K.

- Provider: Google
- Credits: 350 (per image (1K/2K), 700 credits for 4K)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: image_input=[], aspect_ratio=match_input_image, resolution=2K, output_format=jpg, safety_filter_level=block_only_high, allow_fallback_model=false
- Example input:
```json
{
  "model": "google/nano-banana-pro",
  "input": {
    "prompt": "35.6586° N, 139.7454° E at 19:00",
    "resolution": "2K",
    "aspect_ratio": "4:3",
    "output_format": "png"
  }
}
```
- Full docs: https://console.core.today/docs/models/google/nano-banana-pro

### NSFW Image Detection — `falcons-ai/nsfw_image_detection`

The standard NSFW image classifier (127M+ runs) — returns 'normal' or 'nsfw' for any image. An essential, ultra-cheap moderation gate for UGC platforms.

- Provider: Falcons.ai
- Credits: 1 (per image)
- Speed: fast / Quality: high
- Required params: image (string)
- Example input:
```json
{
  "model": "falcons-ai/nsfw_image_detection",
  "input": {
    "image": "https://example.com/user-upload.jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/falcons-ai/nsfw_image_detection

### Pruna P-Image — `prunaai/p-image`

Pruna AI's distilled text-to-image model optimized for extremely low-cost, high-throughput generation. One of the most-run community models on Replicate (15.6M+ runs) thanks to its speed and price.

- Provider: Pruna AI
- Credits: 12 (per image)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: aspect_ratio=16:9, width, height, prompt_upsampling=false, seed, disable_safety_checker=false, lora_weights, lora_scale=0.5, hf_api_token
- Example input:
```json
{
  "model": "prunaai/p-image",
  "input": {
    "prompt": "A minimalist logo concept for a coffee roastery, flat vector style, warm tones",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/prunaai/p-image

### Pruna P-Image Upscale — `prunaai/p-image-upscale`

PrunaAI's high-end image upscaler (575K+ runs) reaching up to 128-megapixel output. Target-megapixel or factor-based control, optional detail/realism enhancement passes, and megapixel-tiered pricing that starts at just 15 credits.

- Provider: Pruna AI
- Credits: 12 (per image at ≤4MP output (default) — tiered by output MP: ≤4MP 12 / ≤8MP 23 / ≤16MP 46 / ≤32MP 92 / ≤64MP 140 / >64MP 270; factor mode bills the top tier (270))
- Speed: medium / Quality: ultra
- Required params: image (string)
- Optional params: upscale_mode=target, target=4, factor=2, enhance_details=false, enhance_realism=false, output_format=jpg, output_quality=80, disable_safety_checker=false, no_op=false
- Example input:
```json
{
  "model": "prunaai/p-image-upscale",
  "input": {
    "image": "https://example.com/photo.jpg",
    "upscale_mode": "target",
    "target": 4
  }
}
```
- Full docs: https://console.core.today/docs/models/prunaai/p-image-upscale

### PhotoMaker — `tencentarc/photomaker`

Generate stylized photos of a person from 1-4 reference photos (9M+ runs). Ten styles including Cinematic, Disney Character, and Digital Art — keep the identity, change everything else.

- Provider: Tencent ARC
- Credits: 10 (per image (num_outputs billed per image))
- Speed: medium / Quality: high
- Required params: input_image (string)
- Optional params: prompt=A photo of a person img, input_image2, input_image3, input_image4, style_name=Photographic (Default), negative_prompt=nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, num_steps=20, style_strength_ratio=20, num_outputs=1, guidance_scale=5, seed, disable_safety_checker=false
- Example input:
```json
{
  "model": "tencentarc/photomaker",
  "input": {
    "input_image": "https://example.com/selfie.jpg",
    "prompt": "portrait photo of a man img, city night background, dramatic lighting",
    "style_name": "Cinematic",
    "num_outputs": 2
  }
}
```
- Full docs: https://console.core.today/docs/models/tencentarc/photomaker

### PhotoMaker Style — `tencentarc/photomaker-style`

The stylization-focused variant of PhotoMaker: turn 1-4 photos of a person into paintings, comics, 3D art, and more with stronger style transfer. Pairs with the base PhotoMaker — use this one when style matters more than photorealism.

- Provider: Tencent ARC
- Credits: 15 (14 credits x num_outputs (1-4 images))
- Speed: medium / Quality: high
- Required params: input_image (string)
- Optional params: prompt=A photo of a person img, input_image2, input_image3, input_image4, style_name=(No style), negative_prompt=nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, num_steps=20, style_strength_ratio=20, num_outputs=1, guidance_scale=5, seed, disable_safety_checker=false
- Example input:
```json
{
  "model": "tencentarc/photomaker-style",
  "input": {
    "input_image": "https://example.com/face.jpg",
    "prompt": "A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation",
    "num_steps": 50,
    "style_name": "(No style)",
    "num_outputs": 2,
    "style_strength_ratio": 35,
    "negative_prompt": "realistic, photo-realistic, worst quality, greyscale, bad anatomy"
  }
}
```
- Full docs: https://console.core.today/docs/models/tencentarc/photomaker-style

### Professional Headshot — `flux-kontext-apps/professional-headshot`

Turn any single photo into a polished professional business headshot, powered by FLUX.1 Kontext [pro]. Pick a background — white, black, gray, neutral, or office — and get a LinkedIn-ready portrait in one step.

- Provider: Black Forest Labs
- Credits: 93 (per image (fixed))
- Speed: fast / Quality: high
- Required params: input_image (string)
- Optional params: seed, gender=none, background=neutral, aspect_ratio=match_input_image, output_format=png, safety_tolerance=2
- Example input:
```json
{
  "model": "flux-kontext-apps/professional-headshot",
  "input": {
    "input_image": "https://example.com/casual-photo.png",
    "gender": "female",
    "background": "neutral",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/flux-kontext-apps/professional-headshot

### Proteus v0.2 — `datacte/proteus-v0.2`

Popular anime-focused image model (12M+ runs) — high-quality anime and illustration styles with img2img and inpainting support. The go-to for anime avatars and webtoon-style art.

- Provider: Proteus
- Credits: 35 (per image (num_outputs billed per image))
- Speed: medium / Quality: high
- Optional params: prompt=black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed, negative_prompt=worst quality, low quality, image, mask, width=1024, height=1024, num_outputs=1, scheduler=KarrasDPM, num_inference_steps=20, guidance_scale=7.5, prompt_strength=0.8, seed, apply_watermark=true, disable_safety_checker=false
- Example input:
```json
{
  "model": "datacte/proteus-v0.2",
  "input": {
    "prompt": "anime girl with silver hair, cherry blossom background, soft lighting, best quality, highly detailed",
    "width": 1024,
    "height": 1024
  }
}
```
- Full docs: https://console.core.today/docs/models/datacte/proteus-v0.2

### PuLID — `bytedance/pulid`

ByteDance PuLID: tuning-free identity customization on SDXL. Give it one face photo and a prompt to generate portraits in any scene or style — no training, 4-step fast sampling, and even two-identity blending. Extremely cost-effective at 2 credits per image.

- Provider: ByteDance
- Credits: 6 (1 credit x num_samples (default 4 images = 6 credits))
- Speed: fast / Quality: high
- Required params: main_face_image (string)
- Optional params: prompt=portrait,color,cinematic,in garden,soft light,detailed face, auxiliary_face_image1, auxiliary_face_image2, auxiliary_face_image3, negative_prompt=flaws in the eyes, flaws in the face, flaws, lowres, non-HDRi, low quality, worst quality,artifacts noise, text, watermark, glitch, deformed, mutated, ugly, disfigured, hands, low resolution, partially rendered objects,  deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed,blurry, cfg_scale=1.2, num_steps=4, image_height=1024, image_width=768, identity_scale=0.8, generation_mode=fidelity, mix_identities=false, seed, num_samples=4, output_format=webp, output_quality=80
- Example input:
```json
{
  "model": "bytedance/pulid",
  "input": {
    "main_face_image": "https://example.com/face.webp",
    "prompt": "portrait, impressionist painting, loose brushwork, vibrant color, light and shadow play",
    "num_samples": 4,
    "identity_scale": 0.8,
    "generation_mode": "fidelity"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/pulid

### Real-ESRGAN — `nightmareai/real-esrgan`

The classic image upscaler (94M+ runs). Real-ESRGAN super-resolution up to 10x with optional GFPGAN face enhancement — the go-to default for cleanly enlarging photos and AI images.

- Provider: Real-ESRGAN
- Credits: 5 (per image)
- Speed: fast / Quality: high
- Required params: image (string)
- Optional params: scale=4, face_enhance=false
- Example input:
```json
{
  "model": "nightmareai/real-esrgan",
  "input": {
    "image": "https://example.com/photo.jpg",
    "scale": 4
  }
}
```
- Full docs: https://console.core.today/docs/models/nightmareai/real-esrgan

### Recraft V4 — `recraft-ai/recraft-v4`

Recraft's next-generation text-to-image model, improving on V3's typography, style range, and prompt adherence for production-grade brand and design assets.

- Provider: Recraft
- Credits: 93 (per image)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=Not set, size=1024x1024
- Example input:
```json
{
  "model": "recraft-ai/recraft-v4",
  "input": {
    "prompt": "A minimalist poster for a coffee shop grand opening, bold headline text 'NOW OPEN', clean sans-serif typography, warm color palette",
    "aspect_ratio": "3:4"
  }
}
```
- Full docs: https://console.core.today/docs/models/recraft-ai/recraft-v4

### Recraft V4 SVG — `recraft-ai/recraft-v4-svg`

Generates vector graphics directly in SVG format using Recraft V4, ideal for logos, icons, and scalable illustrations that need to stay crisp at any size.

- Provider: Recraft
- Credits: 190 (per image)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=Not set, size=1024x1024
- Example input:
```json
{
  "model": "recraft-ai/recraft-v4-svg",
  "input": {
    "prompt": "A minimalist geometric logo mark for a fintech startup, single color, flat vector style, no gradients",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/recraft-ai/recraft-v4-svg

### Recraft V3 — `recraft-ai/recraft-v3`

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. SOTA in image generation per the Artificial Analysis Text-to-Image Benchmark.

- Provider: Recraft
- Credits: 93 (per image)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: size=1024x1024, style=any, aspect_ratio=Not set
- Example input:
```json
{
  "model": "recraft-ai/recraft-v3",
  "input": {
    "prompt": "a wildlife photography photo of a red panda using a laptop in a snowy forest",
    "size": "1365x1024",
    "style": "any"
  }
}
```
- Full docs: https://console.core.today/docs/models/recraft-ai/recraft-v3

### Recraft Crisp Upscale — `recraft-ai/recraft-crisp-upscale`

Fast, affordable upscaler from Recraft designed for sharp, crisp results — a single image input with no tuning needed. Great default for UI assets, illustrations, and product images.

- Provider: Recraft
- Credits: 14 (per image)
- Speed: fast / Quality: high
- Required params: image (string)
- Example input:
```json
{
  "model": "recraft-ai/recraft-crisp-upscale",
  "input": {
    "image": "https://example.com/illustration.png"
  }
}
```
- Full docs: https://console.core.today/docs/models/recraft-ai/recraft-crisp-upscale

### Remove Background — `bria/remove-background`

AI-powered background removal tool for images. Clean, accurate cutouts for any subject with professional-quality edge detection.

- Provider: Bria AI
- Credits: 32 (per image)
- Speed: fast / Quality: high
- Optional params: image, image_url, preserve_alpha=true, content_moderation=false, preserve_partial_alpha=true
- Example input:
```json
{
  "model": "bria/remove-background",
  "input": {
    "image_url": "https://example.com/product-photo.jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/bria/remove-background

### Remove BG — `lucataco/remove-bg`

One of the most-run background removers on Replicate (17M+ runs). A single-parameter API that strips the background and returns a transparent PNG — at just 1 credit per image, the cheapest cutout on the platform.

- Provider: lucataco
- Credits: 1 (per image)
- Speed: fast / Quality: standard
- Required params: image (string)
- Example input:
```json
{
  "model": "lucataco/remove-bg",
  "input": {
    "image": "https://example.com/product.jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/lucataco/remove-bg

### Stable Diffusion XL — `stability-ai/sdxl`

Stability AI's classic SDXL (85M+ runs) — the battle-tested text-to-image model with img2img, inpainting, refiner, and LoRA support. A dependable workhorse with a huge ecosystem.

- Provider: Stability AI
- Credits: 9 (per image (num_outputs billed per image))
- Speed: medium / Quality: high
- Optional params: prompt=An astronaut riding a rainbow unicorn, negative_prompt=, image, mask, width=1024, height=1024, num_outputs=1, scheduler=K_EULER, num_inference_steps=50, guidance_scale=7.5, prompt_strength=0.8, seed, refine=no_refiner, high_noise_frac=0.8, refine_steps, apply_watermark=true, lora_scale=0.6, replicate_weights, disable_safety_checker=false
- Example input:
```json
{
  "model": "stability-ai/sdxl",
  "input": {
    "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
    "width": 1024,
    "height": 1024,
    "refine": "expert_ensemble_refiner"
  }
}
```
- Full docs: https://console.core.today/docs/models/stability-ai/sdxl

### SDXL Lightning 4-step — `bytedance/sdxl-lightning-4step`

ByteDance's 4-step SDXL Lightning — the most-run model on Replicate (1B+ runs). Near-instant 1024px image generation at one of the lowest prices in the catalog.

- Provider: ByteDance
- Credits: 4 (per image (num_outputs billed per image))
- Speed: fast / Quality: standard
- Optional params: prompt=self-portrait of a woman, lightning in the background, negative_prompt=worst quality, low quality, width=1024, height=1024, num_outputs=1, scheduler=K_EULER, num_inference_steps=4, guidance_scale=0, seed=0, disable_safety_checker=false
- Example input:
```json
{
  "model": "bytedance/sdxl-lightning-4step",
  "input": {
    "prompt": "self-portrait of a woman, lightning in the background",
    "width": 1024,
    "height": 1024,
    "num_inference_steps": 4
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/sdxl-lightning-4step

### Seedream 5 Lite — `bytedance/seedream-5-lite`

Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge. Supports multi-reference generation with up to 14 images and sequential batch generation.

- Provider: ByteDance
- Credits: 82 (per image (2K/3K same price; sequential auto bills 81 × max_images))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: image_input=[], size=2K, aspect_ratio=match_input_image, sequential_image_generation=disabled, max_images=1, output_format=png
- Example input:
```json
{
  "model": "bytedance/seedream-5-lite",
  "input": {
    "prompt": "A Renaissance-style oil painting of a modern-day farmer's market. A woman in a hoodie examines heirloom tomatoes under a striped awning, lit like a Vermeer interior. Warm golden Dutch Golden Age light, every detail unmistakably contemporary",
    "size": "2K",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedream-5-lite

### Seedream 5 Pro — `bytedance/seedream-5-pro`

ByteDance's flagship Seedream 5.0 Pro image generation model, with built-in reasoning, precise instruction following, and multi-reference support for up to 10 images. Offers 1K and 2K resolution output with higher fidelity than Seedream 5 Lite.

- Provider: ByteDance
- Credits: 210 (per image, tiered by resolution)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: image_input=[], size=2K, aspect_ratio=match_input_image, output_format=png
- Example input:
```json
{
  "model": "bytedance/seedream-5-pro",
  "input": {
    "prompt": "Combine these three sneaker reference photos into a single studio product shot on a seamless white background, consistent lighting from the upper left, and a soft shadow beneath each shoe",
    "image_input": [
      "https://example.com/sneaker-1.jpg",
      "https://example.com/sneaker-2.jpg",
      "https://example.com/sneaker-3.jpg"
    ],
    "size": "2K",
    "aspect_ratio": "1:1"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedream-5-pro

### Seedream 4.5 — `bytedance/seedream-4.5`

Upgraded ByteDance image model with stronger spatial understanding and world knowledge. Supports single/multi-reference image-to-image editing and sequential (multi-image) generation.

- Provider: ByteDance
- Credits: 90 (per image — sequential mode (auto) scales per generated image, up to max_images (15))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: image_input=[], size=2K, width=2048, height=2048, aspect_ratio=match_input_image, sequential_image_generation=disabled, max_images=1, disable_safety_checker=false
- Example input:
```json
{
  "model": "bytedance/seedream-4.5",
  "input": {
    "prompt": "A warm, nostalgic film-style interior of a cozy café, shot on 35mm-inspired digital photography with soft afternoon sunlight filtering through the front windows.",
    "size": "4K",
    "aspect_ratio": "16:9",
    "sequential_image_generation": "disabled"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedream-4.5

### Seedream 4.0 — `bytedance/seedream-4`

ByteDance's latest image generation model with exceptional prompt understanding and creative capabilities.

- Provider: ByteDance
- Credits: 70 (per image)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: image_input=[], size=2K, aspect_ratio=match_input_image, width=2048, height=2048, sequential_image_generation=disabled, max_images=1, enhance_prompt=true
- Example input:
```json
{
  "model": "bytedance/seedream-4",
  "input": {
    "prompt": "Modern coffee shop interior with text 'OPEN NOW' in neon sign style, cozy atmosphere, Instagram aesthetic",
    "size": "1024x1024"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedream-4

### Text Extract OCR — `abiruyt/text-extract-ocr`

Simple, massively-used OCR (91M+ runs) — extracts text from an image with a single input and returns plain text. Great default for receipts, screenshots, and scanned documents at just 1 credit.

- Provider: OCR
- Credits: 1 (per image)
- Speed: fast / Quality: standard
- Required params: image (string)
- Example input:
```json
{
  "model": "abiruyt/text-extract-ocr",
  "input": {
    "image": "https://example.com/receipt.jpg"
  }
}
```
- Full docs: https://console.core.today/docs/models/abiruyt/text-extract-ocr

### TRELLIS — `firtoz/trellis`

Microsoft's TRELLIS image-to-3D (836K+ runs — the most-used 3D model on Replicate). Turns one or more images into a textured GLB 3D asset, with turntable render videos and optional Gaussian PLY.

- Provider: Microsoft
- Credits: 77 (per generation)
- Speed: medium / Quality: high
- Required params: images (array)
- Optional params: seed=0, randomize_seed=true, generate_color=true, generate_normal=false, generate_model=false, save_gaussian_ply=false, return_no_background=false, ss_guidance_strength=7.5, ss_sampling_steps=12, slat_guidance_strength=3, slat_sampling_steps=12, mesh_simplify=0.95, texture_size=1024
- Example input:
```json
{
  "model": "firtoz/trellis",
  "input": {
    "images": [
      "https://example.com/product.png"
    ],
    "generate_model": true,
    "texture_size": 1024
  }
}
```
- Full docs: https://console.core.today/docs/models/firtoz/trellis

### Google Upscaler — `google/upscaler`

Google's image upscaler (770K+ runs). Upscale images 2x or 4x using generative AI while preserving natural detail, with adjustable output compression — a simple, reliable enhancer at a flat price.

- Provider: Google
- Credits: 46 (per image (x2 and x4 same price))
- Speed: fast / Quality: high
- Required params: image (string)
- Optional params: upscale_factor=x2, compression_quality=80
- Example input:
```json
{
  "model": "google/upscaler",
  "input": {
    "image": "https://example.com/photo.jpg",
    "upscale_factor": "x4",
    "compression_quality": 95
  }
}
```
- Full docs: https://console.core.today/docs/models/google/upscaler

### Z-Image Turbo — `prunaai/z-image-turbo`

Pruna's ultra-fast Z-Image Turbo (48M+ runs). Megapixel-priced image generation up to 2048x2048 — pay exactly for the resolution you generate, with excellent price/performance for high-volume use.

- Provider: Pruna AI
- Credits: 40 (per megapixel (1024x1024 = 40, 2048x2048 = 160, 512x512 = 10))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: height=1024, width=1024, num_inference_steps=8, guidance_scale=0, seed, go_fast=false, output_format=jpg, output_quality=80
- Example input:
```json
{
  "model": "prunaai/z-image-turbo",
  "input": {
    "prompt": "A cozy coffee shop interior, warm lighting, photorealistic",
    "width": 1024,
    "height": 1024
  }
}
```
- Full docs: https://console.core.today/docs/models/prunaai/z-image-turbo