gdhe17/Self-Forcing
text-to-video model by gdhe17
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion Paper | Website | Models (HuggingFace) | Code Self Forcing trains autoregressive video diffusion models by simulating the inference process during training, performing autoregressive rollout with KV caching. It resolves the train-test distribution mismatch and enables real-time, streaming video generation on a single RTX 4090 while matching the quality of state-of-the-art diffusion models. We tested this repo on the following setup: Other hardware setup could also work but hasn't been tested. Create a conda environment and install dependencies: Note: Example inference script using the chunk-wise autoregressive checkpoint trained with DMD: Other config files and corresponding checkpoints can be found in configs folder and our huggingface repo. Note: Our training algorithm (except for the GAN version) is data-free (no video data is needed). For now, we directly provide the ODE initialization checkpoint…
Read the full model card ↗ · Preview checked 2026-10-29T00:25:44.580Z
Inside the original model card — Document outline
- Requirements
- Installation
- Quick Start
- Download checkpoints
- GUI demo
- CLI Inference
- Training
- Download text prompts and ODE initialized checkpoint
- Self Forcing Training with DMD
- Acknowledgements
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
gdhe17/Self-Forcing is a text-to-video model repository published by gdhe17 on Hugging Face. The source reports the self-forcing library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- self-forcing
- Recent downloads (30 days)
- 11,917
- Cumulative likes
- 131
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2025-06-09T01:51:59.000Z
- Last modified
- 2025-09-23T07:43:48.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:32.159Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack/Wan2.2-T2V-A14B-GGUF