Efficient-Large-Model/SANA-Video_2.0_5B_720p_4step
text-to-video model by Efficient-Large-Model
Older snapshot: check the original source for current information.
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.
Project page · Online demo · Documentation · GitHub · Paper SANA-Video 2.0 is an efficient diffusion transformer for high-resolution video generation. This preview provides the latest global-step-1000 full-model EMA checkpoint distilled for four-stage text-to-video generation at 720p, plus an auxiliary RL LoRA for post-hoc strength adjustment. It combines gated bidirectional linear-attention layers with periodic dense softmax-attention anchors and shared Attention Residual aggregation. The selected checkpoint is the latest global-step-1000 tri-temporal DMD EMA export initialized from the SANA-Video 2.0 SFT model after merging the ReFL step-500 adapter. DMD then updates the full transformer; the primary release artifact is therefore a full model, not a LoRA adapter. The checkpoint contains a statedictema tensor mapping only. It does not contain optimizer, learning-rate scheduler, gradient-scaler, or training-loop state. The inference entry point unwraps statedictema, removes an optional model. key prefix, and casts the transformer to BF16. The separately released rank-128 RL LoRA contains…
Read the full model card ↗ · Preview checked 2026-10-29T00:18:41.329Z
Inside the original model card — Document outline
- SANA-Video 2.0 5B 720p — 4-Step Preview
- Model details
- Checkpoint lineage and format
- Files
- Verified 4-step example
- Four-stage sampling contract
- Online preview
- Local inference
- Intended use
- Limitations and bias
- Resources
- 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
Efficient-Large-Model/SANA-Video_2.0_5B_720p_4step is a text-to-video model repository published by Efficient-Large-Model on Hugging Face. The source reports the sana 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
- sana
- Recent downloads (30 days)
- 2,606
- Cumulative likes
- 5
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-08-27T08:11:49.000Z
- Last modified
- 2026-09-08T04:54:26.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: Efficient-Large-Model/SANA-Video_2.0_5B_720p
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 2026-09-26T06:38:43.614Z. 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