AlibabaFastStandard

Wan 2.2 I2V Fast

A very fast and cheap PrunaAI-optimized version of Alibaba's Wan 2.2 A14B image-to-video model. Turns a single still image plus a prompt into a short animated clip at 480p or 720p, with an optional frame-interpolation pass for smoother motion.

260 credits

per output video (flat, not per-second) — 480p base 120, 480p+interpolate 150, 720p base 260, 720p+interpolate 340

PrunaAI-optimized inference — fast and low-cost compared to the base Wan 2.2 model

Image-to-video with optional last-frame conditioning for smoother transitions

Optional 30 FPS frame interpolation (ffmpeg-based) for silkier motion

480p or 720p output, flat per-video pricing (not per-second)

LoRA support on both the high-noise and low-noise transformers

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "wan-video/wan-2.2-i2v-fast",
  "input": {
    "image": "https://replicate.delivery/pbxt/NRvtedaIOd3pdE0pTE3L9uavxJ53g33THGr0HF81M2olNOce/replicate-prediction-g8gbs3rbk9rme0crbhwatpsq04.jpg",
    "prompt": "Close-up shot of an elderly sailor wearing a yellow raincoat, seated on the deck of a catamaran, slowly puffing on a pipe. His cat lies quietly beside him with eyes closed, enjoying the calm. The warm glow of the setting sun bathes the scene, with gentle waves lapping against the hull and a few seabirds circling slowly above. The camera slowly pushes in, capturing this peaceful and harmonious moment.",
    "resolution": "480p",
    "go_fast": true
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Prompt for video generation
`image`	string	Yes	-	Input image to generate video from
`last_image`	string	No	-	Optional last image to condition the video generation for smoother transitions
`resolution`	string	No	480p	Resolution of video: 16:9 is 832x480px, 9:16 is 480x832px 480p720p
`interpolate_output`	boolean	No	false	Interpolate the generated video to 30 FPS using ffmpeg (raises price)
`num_frames`	integer	No	81	Number of video frames (81 gives the best results)
`frames_per_second`	integer	No	16	Frames per second. Pricing is based on duration at 16 fps
`go_fast`	boolean	No	true	Go fast (faster inference, no price change)
`sample_shift`	number	No	12	Sample shift factor
`seed`	integer	No	-	Random seed. Leave blank for random
`disable_safety_checker`	boolean	No	false	Disable safety checker for generated video
`lora_weights_transformer`	string	No	-	LoRA weights URL for the HIGH-noise transformer (.safetensors)
`lora_scale_transformer`	number	No	1	How strongly the transformer LoRA is applied
`lora_weights_transformer_2`	string	No	-	LoRA weights URL for the LOW-noise transformer_2 (.safetensors)
`lora_scale_transformer_2`	number	No	1	How strongly the transformer_2 LoRA is applied

How to Provide File Input

There are 3 ways to provide files for the imagelast_imagelora_weights_transformerlora_weights_transformer_2 parameters:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=wan-video/wan-2.2-i2v-fast" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:image=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "wan-video/wan-2.2-i2v-fast",
  "input": {
    "prompt": "your prompt here",
    "image": "https://example.com/image.jpg"
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

480p Base Animation

Fast, low-cost image-to-video at the default 480p resolution

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "wan-video/wan-2.2-i2v-fast",
  "input": {
    "image": "https://replicate.delivery/pbxt/NRvtedaIOd3pdE0pTE3L9uavxJ53g33THGr0HF81M2olNOce/replicate-prediction-g8gbs3rbk9rme0crbhwatpsq04.jpg",
    "prompt": "Close-up shot of an elderly sailor wearing a yellow raincoat, seated on the deck of a catamaran, slowly puffing on a pipe. His cat lies quietly beside him with eyes closed, enjoying the calm. The warm glow of the setting sun bathes the scene, with gentle waves lapping against the hull and a few seabirds circling slowly above. The camera slowly pushes in, capturing this peaceful and harmonious moment.",
    "resolution": "480p",
    "go_fast": true
  }
}'

720p with Interpolation

Higher resolution output with 30 FPS interpolation for smoother motion

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "wan-video/wan-2.2-i2v-fast",
  "input": {
    "image": "https://replicate.delivery/pbxt/NRvtedaIOd3pdE0pTE3L9uavxJ53g33THGr0HF81M2olNOce/replicate-prediction-g8gbs3rbk9rme0crbhwatpsq04.jpg",
    "prompt": "The same scene, but the camera slowly pulls back to reveal the full catamaran sailing into the sunset",
    "resolution": "720p",
    "interpolate_output": true
  }
}'