Downloads · 30 days
39
18% of all-time downloads
SANA-WM_chunk_causal
Efficient-Large-Model/SANA-WM_chunk_causal
SANA-WM_chunk_causal is a text-to-video model from Efficient-Large-Model. Use it when you need video from a text prompt. The card lists the license as apache-2.0.
This repository contains the chunk-causal Stage-1 teacher DiT checkpoint for SANA-WM. It is intended to be used with the public SANA-WM code and reuses the VAE and refiner from Efficient-Large-Model/SANA-WMbidirectional.
All-time downloads
217
Public
Repo size
10.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.7 GB · 100%
At a glance
- Task
- Text-to-Video
- License
- apache-2.0
- Access
- Public
- Created
- Jun 10, 2026
- Updated
- Jul 31, 2026
- SHA
- ef7ea10f
Base models
Model card
From the Hugging Face model README
SANA-WM Chunk-Causal Stage-1 Teacher
This repository contains the chunk-causal Stage-1 teacher DiT checkpoint for SANA-WM.
It is intended to be used with the public SANA-WM code and reuses the VAE and refiner from Efficient-Large-Model/SANA-WM_bidirectional.
Files
config.yaml: inference config withscheduler.vis_sampler: chunk_flow_euler.dit/sana_wm_chunk_causal_1600m_720p.safetensors: chunk-causal Stage-1 teacher checkpoint.
Inference
python inference_video_scripts/wm/inference_sana_wm.py \
--config hf://Efficient-Large-Model/SANA-WM_chunk_causal/config.yaml \
--model_path hf://Efficient-Large-Model/SANA-WM_chunk_causal/dit/sana_wm_chunk_causal_1600m_720p.safetensors \
--image asset/sana_wm/demo_0.png \
--prompt asset/sana_wm/demo_0.txt \
--action "w-80,jw-40,w-40,lw-60,w-100" \
--num_frames 961 \
--output_dir results/sana_wm_chunk_causal
The sampler uses interval_k = 1 / num_chunks by default.
- Task
- Text-to-Video
- License
- apache-2.0
- Created
- Jun 10, 2026
- Updated
- Jul 31, 2026