Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About CausVid
Generate video progressively with a distilled causal diffusion model supporting streaming and dynamic prompts. Converts a bidirectional diffusion transformer into an autoregressive generator and distills the sampling process to four steps.
Key features
Provides inference and distillation code for streaming text-to-video, video-to-video and image-conditioned experiments.
Getting started
Open the official repository, read its current README and licence, then follow the documented environment, checkpoint and inference steps. Start with the supplied example before using your own media or data.
Real-time interaction
Converts a bidirectional diffusion transformer into an autoregressive generator and distills the sampling process to four steps.
Pricing
CC BY-NC-SA 4.0; compute costs extra Repository code: CC BY-NC-SA 4.0. Model weights and dependencies may have separate terms. No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.
Limitations
The repository licence is non-commercial and share-alike, so public source availability does not make it unrestricted open-source software.
EDITORIAL VIEW
Editor's Verdict
Consider CausVid if its documented workflow matches your experiment; start from the linked repository rather than an unofficial mirror.
Check the licence and run a small local evaluation before choosing it for production. No ratings or measured results are inferred from its publication.
How It Works
- Converts a bidirectional diffusion transformer into an autoregressive generator and distills the sampling process to four steps.
What We Like
- Provides inference and distillation code for streaming text-to-video, video-to-video and image-conditioned experiments.
Current Limitations
- The repository licence is non-commercial and share-alike, so public source availability does not make it unrestricted open-source software.
Pricing & Access
- Repository code: CC BY-NC-SA 4.0. Model weights and dependencies may have separate terms.
- No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.
Verification Summary
- Official repository and licence reviewed on 2026-09-14. Video Runtime has not installed or benchmarked this project.
- This is a source review, not verification of demo uptime, output quality or performance on your hardware.
Technical notes & official performance
Official Performance Data
- The authors report 9.4 FPS on a single GPU. This is an official claim, not a Video Runtime benchmark or end-to-end latency measurement.
Technical Notes
- KV caching and causal attention enable progressive output; model assets and dependencies retain their own terms.
Sources
- Official GitHub repository ↗github · accessed 2026-09-14
- Code licence ↗github · accessed 2026-09-14
Access, stage & mechanism
These are separate source-checked facts, not a live uptime monitor. Unverified fields are left open; transport and persistent sessions do not establish how frames are generated.
- Release stage
- Not verified
- Access mode
- Not verified
- Source availability
- Not verified
- Transport
- Not verified
- Interaction
- Not verified
- Session mode
- Not verified
- Generation mechanism
- Not verified
- Continuity method
- Not verified
- Licence status
- Not verified
- Tasks
- Not classified
CONTINUE EXPLORING
Related projects & models
Selected by research links and category, not by popularity.
Train few-step autoregressive video generators with frame-wise and chunk-wise Causal Forcing variants.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU requiredA research baseline for streaming video generation that trains models on their own autoregressive outputs.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU requiredStudy streaming video-to-video stylization with feature banks that reuse information from earlier frames.
A related project selected in this entry’s research.Public repository; self-hosted setup and compatible GPU required
Run an action-conditioned interactive world model with open-ended rollout on a single desktop GPU.
Another frame streaming option in this section.Public repository; self-hosted installation and compatible GPU requiredRead how official-source and hands-on records stay separate in our Methodology.