Sign inGet started
ReplicateText to videoComing soon

bytedance/dreamactor-m2.0

bytedance/dreamactor-m2.0 is a text 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.

Price pending

Pricing

Price pending.

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

FieldKindDefaultDescription
image requiredURL or file—Input image containing a human subject. Supported formats: JPEG, JPG, PNG. Max size: 4.7 MB. Resolution: 480x480 to 1920x1080.
video requiredtext—Template video whose motion, facial expressions, and lip movements will be applied to the image subject. Supported formats: MP4, MOV, WebM. Max duration: 30 seconds. Resolution: 200x200 to 2048x1440.
cut_first_secondtrue or falsetrueWhether to crop the first second of the output video (removes the 1-second transition at the beginning).

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": "bytedance/dreamactor-m2.0",
    "input": {
      "image": "<image>",
      "video": "<video>"
    }
  }'