Video
AnimateDiff
AnimateDiff creates brief animated scenes from a text prompt.
- Text to video
- Video editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for AnimateDiff. Review your own result before publishing.
A starting point.
Try a single visual idea with one clear subject action and restrained camera movement.
Before you publish.
Watch for flicker, changing faces and abrupt motion between the first and last frames.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Choose num_frames from 1–32 and fps from 1–16 together; frame count and playback rate determine clip length.
Use motions only for supported motion choices. Video-to-video instead needs video_url and prompt, with strength controlling the transformation.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for fast-animatediff/text-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
fps | Whole number | Optional | ≥ 1 · ≤ 16 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
motions | List | Optional | — |
negative_prompt | Text | Optional | — |
num_frames | Whole number | Optional | ≥ 1 · ≤ 32 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 50 |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Video editingfast-animatediff/video-to-video
Supported inputs
These fields come from the current studio form for fast-animatediff/video-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
video_url | Text | Required | — |
first_n_seconds | Whole number | Optional | ≥ 2 · ≤ 4 |
fps | Whole number | Optional | ≥ 1 · ≤ 16 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
motions | List | Optional | — |
negative_prompt | Text | Optional | — |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 50 |
seed | Whole number | Optional | — |
strength | Number | Optional | ≥ 0 · ≤ 1 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use AnimateDiff through the API.
Start with this model ID for the endpoint featured on this page:
fast-animatediff/text-to-video
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-video ·
fast-animatediff/text-to-video - video-to-video ·
fast-animatediff/video-to-video
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.