Nv labs GitHub repo/nv labs GitHub repo main (#163)

* upload 4bit inference code; Signed-off-by: lawrence-cj <[email protected]> * fix import bug; Signed-off-by: lawrence-cj <[email protected]> * 1. update diffusers vae tiling setting for 4K images generation; 2. pre-commit; Signed-off-by: lawrence-cj <[email protected]> * docs: update README.md (#151) supper -> super * fix: correct CSS property & missing articles (#152) - Correct "border-raduis" to "border-radius" - Insert missing article "a" in "modern giant diffusion model" - Insert missing article "a" in "decoder-only small LLM" * 1. update for 4bit Sana; 2. update README.md; 3. update for DCAE-1.1 Signed-off-by: lawrence-cj <[email protected]> * fix the bug for `AutoencoderDC` encode training; (#158) Signed-off-by: lawrence-cj <[email protected]> * pre-commit; Signed-off-by: lawrence-cj <[email protected]> --------- Signed-off-by: lawrence-cj <[email protected]> Co-authored-by: Ikko Eltociear Ashimine <[email protected]> Co-authored-by: CharlesCNorton <[email protected]>
NVlabs · Jan 24, 2025 · e818e73 · e818e73 · Pevernow · Jan 27, 2025
1 parent 9427b26
commit e818e73
Show file tree

Hide file tree

Showing 5 changed files with 846 additions and 9 deletions.
diff --git a/README.md b/README.md
@@ -4,6 +4,8 @@
 
 # ⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
 
+### <div align="center"> ICLR 2025 <div>
+
 <div align="center">
   <a href="https://nvlabs.github.io/Sana/"><img src="https://img.shields.io/static/v1?label=Project&message=Github&color=blue&logo=github-pages"></a> &ensp;
   <a href="https://hanlab.mit.edu/projects/sana/"><img src="https://img.shields.io/static/v1?label=Page&message=MIT&color=darkred&logo=github-pages"></a> &ensp;
@@ -36,18 +38,24 @@ As a result, Sana-0.6B is very competitive with modern giant diffusion models (e
 
 ## 🔥🔥 News
 
-- (🔥 New) \[2025/1/12\] DC-AE tiling makes Sana-4K inferences 4096x4096px images within 22GB GPU memory.[\[Guidance\]](asset/docs/model_zoo.md#-3-4k-models)
+- (🔥 New) \[2025/1/24\] 4bit-Sana is released, powered by [SVDQuant and Nunchaku](https://github.com/mit-han-lab/nunchaku) inference engine. Now run your Sana within **8GB** GPU VRAM [\[Guidance\]](asset/docs/4bit_sana.md) [\[Demo\]](https://svdquant.mit.edu/) [\[Model\]](asset/docs/model_zoo.md)
+- (🔥 New) \[2025/1/24\] DCAE-1.1 is released, better reconstruction quality. [\[Model\]](https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.1) [\[diffusers\]](https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers)
+- (🔥 New) \[2025/1/23\] Sana is accepted by ICLR-2025. 🎉🎉🎉
+
+______________________________________________________________________
+
+- (🔥 New) \[2025/1/12\] DC-AE tiling makes Sana-4K inferences 4096x4096px images within 22GB GPU memory. With model offload and 8bit/4bit quantize. The 4K Sana run within **8GB** GPU VRAM. [\[Guidance\]](asset/docs/model_zoo.md#-3-4k-models)
 - (🔥 New) \[2025/1/11\] Sana code-base license changed to Apache 2.0.
 - (🔥 New) \[2025/1/10\] Inference Sana with 8bit quantization.[\[Guidance\]](asset/docs/8bit_sana.md#quantization)
 - (🔥 New) \[2025/1/8\] 4K resolution [Sana models](asset/docs/model_zoo.md) is supported in [Sana-ComfyUI](https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels) and [work flow](asset/docs/ComfyUI/Sana_FlowEuler_4K.json) is also prepared. [\[4K guidance\]](asset/docs/ComfyUI/comfyui.md)
 - (🔥 New) \[2025/1/8\] 1.6B 4K resolution [Sana models](asset/docs/model_zoo.md) are released: [\[BF16 pth\]](https://huggingface.co/Efficient-Large-Model/Sana_1600M_4Kpx_BF16) or [\[BF16 diffusers\]](https://huggingface.co/Efficient-Large-Model/Sana_1600M_4Kpx_BF16_diffusers). 🚀 Get your 4096x4096 resolution images within 20 seconds! Find more samples in [Sana page](https://nvlabs.github.io/Sana/). Thanks [SUPIR](https://github.com/Fanghua-Yu/SUPIR) for their wonderful work and support.
 - (🔥 New) \[2025/1/2\] Bug in the `diffusers` pipeline is solved. [Solved PR](https://github.com/huggingface/diffusers/pull/10431)
 - (🔥 New) \[2025/1/2\] 2K resolution [Sana models](asset/docs/model_zoo.md) is supported in [Sana-ComfyUI](https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels) and [work flow](asset/docs/ComfyUI/Sana_FlowEuler_2K.json) is also prepared.
-- (🔥 New) \[2024/12/20\] 1.6B 2K resolution [Sana models](asset/docs/model_zoo.md) are released: [\[BF16 pth\]](https://huggingface.co/Efficient-Large-Model/Sana_1600M_2Kpx_BF16) or [\[BF16 diffusers\]](https://huggingface.co/Efficient-Large-Model/Sana_1600M_2Kpx_BF16_diffusers). 🚀 Get your 2K resolution images within 4 seconds! Find more samples in [Sana page](https://nvlabs.github.io/Sana/). Thanks [SUPIR](https://github.com/Fanghua-Yu/SUPIR) for their wonderful work and support.
-- (🔥 New) \[2024/12/18\] `diffusers` supports Sana-LoRA fine-tuning! Sana-LoRA's training and convergence speed is super fast. [\[Guidance\]](asset/docs/sana_lora_dreambooth.md) or  [\[diffusers docs\]](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sana.md).
-- (🔥 New) \[2024/12/13\] `diffusers` has Sana! [All Sana models in diffusers safetensors](https://huggingface.co/collections/Efficient-Large-Model/sana-673efba2a57ed99843f11f9e) are released and diffusers pipeline `SanaPipeline`, `SanaPAGPipeline`, `DPMSolverMultistepScheduler(with FlowMatching)` are all supported now. We prepare a [Model Card](asset/docs/model_zoo.md) for you to choose.
-- (🔥 New) \[2024/12/10\] 1.6B BF16 [Sana model](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16) is released for stable fine-tuning.
-- (🔥 New) \[2024/12/9\] We release the [ComfyUI node](https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels) for Sana. [\[Guidance\]](asset/docs/ComfyUI/comfyui.md)
+- ✅ \[2024/12\] 1.6B 2K resolution [Sana models](asset/docs/model_zoo.md) are released: [\[BF16 pth\]](https://huggingface.co/Efficient-Large-Model/Sana_1600M_2Kpx_BF16) or [\[BF16 diffusers\]](https://huggingface.co/Efficient-Large-Model/Sana_1600M_2Kpx_BF16_diffusers). 🚀 Get your 2K resolution images within 4 seconds! Find more samples in [Sana page](https://nvlabs.github.io/Sana/). Thanks [SUPIR](https://github.com/Fanghua-Yu/SUPIR) for their wonderful work and support.
+- ✅ \[2024/12\] `diffusers` supports Sana-LoRA fine-tuning! Sana-LoRA's training and convergence speed is super fast. [\[Guidance\]](asset/docs/sana_lora_dreambooth.md) or  [\[diffusers docs\]](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sana.md).
+- ✅ \[2024/12\] `diffusers` has Sana! [All Sana models in diffusers safetensors](https://huggingface.co/collections/Efficient-Large-Model/sana-673efba2a57ed99843f11f9e) are released and diffusers pipeline `SanaPipeline`, `SanaPAGPipeline`, `DPMSolverMultistepScheduler(with FlowMatching)` are all supported now. We prepare a [Model Card](asset/docs/model_zoo.md) for you to choose.
+- ✅ \[2024/12\] 1.6B BF16 [Sana model](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16) is released for stable fine-tuning.
+- ✅ \[2024/12\] We release the [ComfyUI node](https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels) for Sana. [\[Guidance\]](asset/docs/ComfyUI/comfyui.md)
 - ✅ \[2024/11\] All multi-linguistic (Emoji & Chinese & English) SFT models are released: [1.6B-512px](https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_MultiLing), [1.6B-1024px](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_MultiLing), [600M-512px](https://huggingface.co/Efficient-Large-Model/Sana_600M_512px), [600M-1024px](https://huggingface.co/Efficient-Large-Model/Sana_600M_1024px). The metric performance is shown [here](#performance)
 - ✅ \[2024/11\] Sana Replicate API is launching at [Sana-API](https://replicate.com/chenxwh/sana).
 - ✅ \[2024/11\] 1.6B [Sana models](https://huggingface.co/collections/Efficient-Large-Model/sana-673efba2a57ed99843f11f9e) are released.