guandeh17/Self-Forcing
Research codebase for training autoregressive video diffusion models with KV caching to enable real-time streaming video generation.
Not currently ranked — collecting fresh signals.
star history
Self Forcing addresses the train-test distribution mismatch in autoregressive video diffusion by simulating the inference process during training, using KV caching and autoregressive rollout. It enables real-time streaming video generation on a single RTX 4090 GPU while achieving quality comparable to state-of-the-art diffusion models. The project provides model weights on HuggingFace and implementation code for training and inference with the Wan2.1-T2V-1.3B base model.
Frequently asked
- What is guandeh17/Self-Forcing?
- Research codebase for training autoregressive video diffusion models with KV caching to enable real-time streaming video generation.
- Is Self-Forcing open source?
- Yes — guandeh17/Self-Forcing is open source, released under the Apache-2.0 license.
- What language is Self-Forcing written in?
- guandeh17/Self-Forcing is primarily written in Python.
- How popular is Self-Forcing?
- guandeh17/Self-Forcing has 3.4k stars on GitHub.
- Where can I find Self-Forcing?
- guandeh17/Self-Forcing is on GitHub at https://github.com/guandeh17/Self-Forcing.