ReplicateImage to videoComing soon

wan-video/wan2.6-i2v-flash

Name: wan-video/wan2.6-i2v-flash
Brand: Replicate

wan-video/wan2.6-i2v-flash is an image to video tool from Replicate that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

resolution: 720p (default) $0.065, 1080p $0.0975 per second. Billed on duration, default 5.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`image` required	URL or file	—	Input image for video generation
`prompt` required	text	—	Text prompt for video generation
`seed`	number (whole)	—	Random seed for reproducible generation
`audio`	URL or file	—	Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization
`duration`	JSON	5	Duration of the generated video in seconds
`resolution`	JSON	720p	Video resolution
`multi_shots`	true or false	false	Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is enabled). True enables multi-shot segmentation, false generates single-shot content.
`audio_enabled`	true or false	true	Whether to generate video with audio. When enabled, the model will auto-generate audio or use provided audio file. Disable for silent video output.
`negative_prompt`	text		Negative prompt to avoid certain elements
`enable_prompt_expansion`	true or false	true	If set to true, the prompt optimizer will be enabled

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "wan-video/wan2.6-i2v-flash",
    "input": {
      "image": "<image>",
      "prompt": "<prompt>"
    }
  }'