Views
No views yet
https://github.com/Pollyannnna/Sana-CameraVideo/data/share/lijiang/ckpt/multi-agent-wm/Sana/SANA-Video_2B_480p/checkpoints/SANA_Video_2B_480p.pth/data/share/lijiang/ckpt/multi-agent-wm/Sana/SANA-Video_2B_480p/vae/Wan2.1_VAE.pth/data/share/Worldmem-VPT/training/vpt/data/share/lijiang/data/mutli-agent-wm/solaris/datasets/solaris-training-dataset/duet/trainlatest-step* folder has:full_state/: full Accelerate/FSDP resume state (metadata.pth, model/pytorch_model_fsdp.bin, model/optimizer.bin, model/scheduler.bin, random states). Use this for same-topology exact resume.model_only/: model-only .pth sidecar. Use this for inference or cross-topology continuation with optimizer reset and train.start_global_step set to the step in the folder name.run_state/: config, selected git history, W&B run id when available, and train log.manifests/latest_status.json: code commits, source paths, and stage metadata.| Stage | Step | Path | Resume note |
|---|---|---|---|
| Stage1 4-GPU no-prompt final lane | 89500 | stage1/stage1-4g-final/latest-step89500 | Use full_state/ for same 4-rank resume, or model_only/epoch_32_step_89500.pth for model-only continuation. |
| Stage1 16-GPU no-prompt continuation | 37500 | stage1/stage1-16g-np/latest-step37500 | Use the one-token no-prompt text shim; do not resume with prompt/Gemma config. |
| Stage1 learned null seed lane | 10500 | stage1/stage1-text-null/latest-step10500 | Clean Stage1 seed used by Solaris duet Stage2. |
| Stage2 Solaris duet | 15000 | stage2/solaris-duet/latest-step15000 | Multiplayer Stage2 state initialized from Stage1 text-null. |
1git lfs install
2git clone https://huggingface.co/<owner>/sana-camera-latest-states1git clone https://github.com/Pollyannnna/Sana-CameraVideo.git
2cd Sana-CameraVideo
3git checkout stage2 # or stage1 / stage1-text-null as needed