Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+demo/sana_video2_5b_720p_4step_rooster_seed4_poster.png filter=lfs diff=lfs merge=lfs -text
+demo/sana_video2_5b_720p_4step_rooster_seed4.mp4 filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Nvidia
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,199 @@
+---
+license: apache-2.0
+library_name: sana
+pipeline_tag: text-to-video
+base_model: Efficient-Large-Model/SANA-Video_2.0_5B_720p
+language:
+  - en
+  - zh
+tags:
+  - text-to-video
+  - SANA
+  - SANA-Video
+  - SANA-Video-2.0
+  - 720p
+  - diffusion
+  - DMD
+  - few-step
+  - LTX-2.3
+---
+
+# SANA-Video 2.0 5B 720p — 4-Step Preview
+
+> **Research preview:** This distilled checkpoint is an early T2V-only preview.
+> For the original 50-step T2V + TI2V release, use
+> [`SANA-Video_2.0_5B_720p`](https://huggingface.co/Efficient-Large-Model/SANA-Video_2.0_5B_720p).
+
+[Project page](https://nvlabs.github.io/Sana/Video2/) ·
+[Online demo](https://huggingface.co/spaces/Efficient-Large-Model/sana-video2-5b-720p-demo) ·
+[Documentation](https://nvlabs.github.io/Sana/docs/sana_video2/) ·
+[GitHub](https://github.com/NVlabs/Sana) ·
+[Paper](https://arxiv.org/abs/2607.21553)
+
+SANA-Video 2.0 is an efficient diffusion transformer for high-resolution video
+generation. This preview provides a full-model EMA checkpoint distilled for
+four-stage text-to-video generation at 720p. It combines gated bidirectional
+linear-attention layers with periodic dense softmax-attention anchors and
+shared Attention Residual aggregation.
+
+## Model details
+
+| Property | Value |
+| --- | --- |
+| Architecture | `SanaVideo2_5B` |
+| Parameters | 4,466,980,960 model parameters (4.47B) |
+| Transformer | 32 layers, hidden size 2,560 |
+| Attention | 75% gated linear attention, 25% dense softmax anchors |
+| Attention Residuals | Shared, timestep-independent aggregation every 8 layers |
+| Task | Text-to-video only |
+| Output bucket | 736 × 1280, 81 frames, 16 FPS (about 5.06 seconds) |
+| Model construction | Source tower at 480; explicit dynamic 736 × 1280 bucket |
+| Text encoder | `google/gemma-2-2b-it` |
+| VAE | LTX 2.3, 128 latent channels, stride `(8, 32, 32)` |
+| Inference | BF16, CFG 1, 4 stages, `sana_shift6_dpm`, no motion suffix |
+| License | Apache 2.0 |
+
+## Checkpoint lineage and format
+
+The selected checkpoint is the global-step-1000 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; this release is therefore a full model,
+**not a LoRA adapter**.
+
+The checkpoint contains a `state_dict_ema` tensor mapping only. It does not
+contain optimizer, learning-rate scheduler, gradient-scaler, or training-loop
+state. The inference entry point unwraps `state_dict_ema`, removes an optional
+`model.` key prefix, and casts the transformer to BF16.
+
+## Files
+
+- `checkpoints/SANA_Video_2.0_5B_720p_4step.pth`: distilled EMA transformer
+- `config.yaml`: clean 5B source-tower config with the preview frame/FPS defaults
+- `demo/`: verified seed-4 MP4 and poster generated from this checkpoint
+- `LICENSE`: Apache License 2.0
+
+## Verified 4-step example
+
+This 1280 × 736, 81-frame, 16 FPS sample was generated from the released
+checkpoint with seed 4 and the exact command shown below.
+
+<p align="center">
+  <a href="https://huggingface.co/Efficient-Large-Model/SANA-Video_2.0_5B_720p_4step/resolve/main/demo/sana_video2_5b_720p_4step_rooster_seed4.mp4">
+    <img src="https://huggingface.co/Efficient-Large-Model/SANA-Video_2.0_5B_720p_4step/resolve/main/demo/sana_video2_5b_720p_4step_rooster_seed4_poster.png" width="90%" alt="SANA-Video 2.0 5B four-step preview: a cartoon rooster holding a beer bottle in a floral vintage room"/>
+  </a>
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/Efficient-Large-Model/SANA-Video_2.0_5B_720p_4step/resolve/main/demo/sana_video2_5b_720p_4step_rooster_seed4.mp4">▶ Watch or download the verified four-step video</a>
+</p>
+
+> **Prompt:** In a cozy, vintage room adorned with floral wallpaper, a cartoon
+> rooster sits comfortably in a floral-patterned armchair, sipping from a bottle
+> of beer. The rooster, with its vibrant red comb and wattle, displays a range of
+> expressions—smiling, nodding, and opening its beak wide in a cheerful manner.
+> The setting includes wooden furniture and another beer bottle on the table,
+> adding to the relaxed atmosphere. The camera captures the rooster from a
+> close-up angle, emphasizing its animated movements and lively demeanor.
+
+## Four-stage sampling contract
+
+This model does not use a truncated DPM-Solver trajectory. At each fixed stage,
+the model predicts velocity `v`, computes `x0 = x - sigma * v`, and—except at
+the terminal stage—re-noises `x0` at the next sigma with a fresh draw from the
+same seeded generator.
+
+| Stage | Physical sigma | API timestep | Model embedding timestep |
+| ---: | ---: | ---: | ---: |
+| 1 | 0.9998332262 | 999.8332262 | 999 |
+| 2 | 0.9471688271 | 947.1688271 | 947 |
+| 3 | 0.8568977118 | 856.8977118 | 856 |
+| 4 | 0.6663702130 | 666.3702130 | 666 |
+
+The rollout uses one BF16 initial-noise draw and three BF16 transition-noise
+draws. `flow_shift` is not applied by this sampler.
+
+## Inference
+
+Until the upstream PR is merged, use the preview branch:
+
+```bash
+git clone https://github.com/Efficient-Large-Model/Sana.git
+cd Sana
+git checkout feat/sana-video2-4step-preview
+bash environment_setup.sh sana
+conda activate sana
+```
+
+Place the Diffusers-format LTX 2.3 VAE at
+`output/pretrained_models/LTX-2.3-Diffusers/`, or update
+`vae.vae_pretrained` in the config.
+
+The following command uses the exact public preview settings:
+
+```bash
+bash inference_video_scripts/inference_sana_video.sh \
+  --np 1 \
+  --config configs/sana_video2/SanaVideo2_5B_720p.yaml \
+  --model_path hf://Efficient-Large-Model/SANA-Video_2.0_5B_720p_4step/checkpoints/SANA_Video_2.0_5B_720p_4step.pth \
+  --txt_file=asset/samples/sana_video2_5b_720p_demo.txt \
+  --task=t2v \
+  --model.image_size=480 \
+  --custom_height_width='[736,1280]' \
+  --sampling_algo=fastvideo_dmd_4step \
+  --generator_sigma_profile=sana_shift6_dpm \
+  --cfg_scale=1.0 \
+  --flow_shift=1.0 \
+  --motion_score=0 \
+  --negative_prompt=None \
+  --num_frames=81 \
+  --step=4 \
+  --fps=16 \
+  --seed=4 \
+  --work_dir output/sana_video2_t2v_720p_4step_preview
+```
+
+The selected global-step-1000 checkpoint was evaluated on the full VBench T2V
+suite: 4,730 prompts across all 16 dimensions, using the same four-stage
+sampling contract, 736×1280 resolution, 81 frames, 16 FPS, and CFG 1.
+
+## Intended use
+
+This model is intended for research, evaluation, and creative generation of
+short videos from text. It can also serve as a full-model starting point for
+further research under the license terms. It is not intended for first-frame
+image conditioning; use the base release for TI2V.
+
+The model is not intended to produce factual evidence, identify people, make
+high-impact automated decisions, or generate content that violates privacy,
+copyright, applicable law, or platform policies.
+
+## Limitations and bias
+
+- This is a research preview and has less extensive release validation than the
+  original 50-step model.
+- Generated motion, anatomy, text rendering, object permanence, and physical
+  interactions may be inconsistent, especially for crowded or highly dynamic
+  scenes.
+- Prompt following can degrade for long, ambiguous, or compositionally complex
+  instructions.
+- Outputs can reflect social and cultural biases present in training data and
+  in the separately loaded text encoder.
+- The model does not independently verify whether generated content is factual,
+  safe, or free of third-party rights.
+
+Users should review outputs before publication, disclose synthetic media where
+appropriate, and add safeguards suited to their application.
+
+## Resources
+
+- [SANA repository](https://github.com/NVlabs/Sana)
+- [SANA-Video 2.0 project page](https://nvlabs.github.io/Sana/Video2/)
+- [SANA-Video 2.0 documentation](https://nvlabs.github.io/Sana/docs/sana_video2/)
+- [Original 50-step 5B 720p model](https://huggingface.co/Efficient-Large-Model/SANA-Video_2.0_5B_720p)
+- [Four-step online preview](https://huggingface.co/spaces/Efficient-Large-Model/sana-video2-5b-720p-demo)
+
+## Citation
+
+If you use SANA-Video, please cite the SANA-Video work linked from the
+[project page](https://nvlabs.github.io/Sana/Video2/). SANA-Video 2.0-specific
+citation information will be added when it becomes available.

checkpoints/SANA_Video_2.0_5B_720p_4step.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206a4f5c5ebeb4076aa2331afca0a63201015dfdc25f42224bbc5d2cc443059b
+size 17871905340

config.yaml

@@ -0,0 +1,94 @@
+task: t2v
+work_dir: output/sana_video2_5b_720p_4step
+report_to: none
+tracker_project_name: sana-video-2
+data:
+  data_dir:
+    video: data/video_toy_data
+  image_size: 720
+  type: SanaZipDataset
+  transform: default_train_video
+  aspect_ratio_type: ASPECT_RATIO_VIDEO_720_MS_DIV32
+  caption_selection_type: proportion
+  caption_proportion:
+    prompt: 1
+  num_frames: 81
+  target_fps: 16
+  resample_fps: false
+model:
+  model: SanaVideo2_5B
+  image_size: 480
+  mixed_precision: bf16
+  fp32_attention: true
+  load_from: null
+  multi_scale: false
+  linear_head_dim: 128
+  softmax_head_dim: 256
+  softmax_ratio: 0.25
+  ffn_type: SwiGLU
+  mlp_ratio: 4.0
+  use_pe: true
+  pos_embed_type: wan_rope
+  qk_norm: true
+  cross_norm: true
+  class_dropout_prob: 0.1
+  attn_res_block_size: 8
+vae:
+  vae_type: LTX2VAE_diffusers
+  vae_pretrained: output/pretrained_models/LTX-2.3-Diffusers
+  weight_dtype: bfloat16
+  vae_latent_dim: 128
+  vae_downsample_rate: 32
+  vae_stride: [8, 32, 32]
+  sample_posterior: false
+  use_causal_encode: true
+text_encoder:
+  text_encoder_name: gemma-2-2b-it
+  caption_channels: 2304
+  y_norm: true
+  y_norm_scale_factor: 0.01
+  model_max_length: 300
+  chi_prompt:
+    - 'Given a user prompt, generate an "Enhanced prompt" that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:'
+    - '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.'
+    - '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.'
+    - 'Here are examples of how to transform or refine prompts:'
+    - '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.'
+    - '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.'
+    - 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:'
+    - 'User Prompt: '
+scheduler:
+  train_sampling_steps: 1000
+  predict_flow_v: true
+  noise_schedule: linear_flow
+  pred_sigma: false
+  learn_sigma: false
+  flow_shift: 6.0
+  inference_flow_shift: 1.0
+  weighting_scheme: logit_normal
+  logit_mean: 0.0
+  logit_std: 0.95
+  vis_sampler: fastvideo_dmd_4step
+train:
+  use_fsdp: true
+  num_workers: 8
+  seed: 4
+  train_batch_size: 1
+  num_epochs: 10
+  gradient_accumulation_steps: 1
+  grad_checkpointing: true
+  gradient_clip: 0.1
+  joint_training_interval: 0
+  optimizer:
+    type: AdamW
+    lr: 5.0e-5
+    betas: [0.9, 0.999]
+    eps: 1.0e-10
+    weight_decay: 0.0
+  auto_lr: null
+  lr_schedule: constant
+  lr_schedule_args:
+    num_warmup_steps: 500
+  log_interval: 10
+  save_model_steps: 1000
+  save_model_epochs: 1

demo/sana_video2_5b_720p_4step_rooster_seed4.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153c34d1284414db231ae33eba51151a8916de65792055c2f4bfc09efb2d49f5
+size 6148452