Video
Stable Video Diffusion
Stable Video Diffusion creates a short video from a scene description.
- Text to video
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Stable Video Diffusion. Review your own result before publishing.
A starting point.
Draft a single-shot motion idea with a stable subject and uncomplicated background.
Before you publish.
Check the ending frame, subject proportions and visible wobble during motion.
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
The documented output has 25 frames; fps sets playback speed rather than generating more frames. Ten fps produces roughly 2.5 seconds.
Use motion_bucket_id for motion amount and cond_aug cautiously. Raywake provides steps from 1–100 and negative_prompt for unwanted visual features.
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-svd/text-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
cond_aug | Number | Optional | ≥ 0 · ≤ 10 |
deep_cache | Text | Optional | — |
fps | Whole number | Optional | ≥ 1 · ≤ 25 |
motion_bucket_id | Whole number | Optional | ≥ 1 · ≤ 255 |
negative_prompt | Text | Optional | — |
seed | Whole number | Optional | — |
steps | Whole number | Optional | ≥ 1 · ≤ 100 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Stable Video Diffusion through the API.
Start with this model ID for the endpoint featured on this page:
fast-svd/text-to-video
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
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.