# Core.Today AI API — Image Tools (Background Removal & Upscaling)

> Background removal, upscaling and face-restoration utility models (Real-ESRGAN, GFPGAN, CodeFormer, Clarity, Topaz, BiRefNet) available through the Core.Today unified API.

Source: https://console.core.today/docs/image-tools
This file: https://console.core.today/llms/image-tools.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 (23)

### 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

### 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

### 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

### 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

### 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

### 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

### 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

### 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

### 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 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

### 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 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

### 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