diffsynth 2.1.9__tar.gz → 2.1.10__tar.gz

{diffsynth-2.1.9 → diffsynth-2.1.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diffsynth
-Version: 2.1.9
+Version: 2.1.10
 Summary: Enjoy the magic of Diffusion models!
 Author: ModelScope Team
 License-Expression: Apache-2.0
@@ -50,7 +50,7 @@ Provides-Extra: infiniteyou
 Requires-Dist: insightface; extra == "infiniteyou"
 Requires-Dist: facexlib; extra == "infiniteyou"
 Provides-Extra: ses
-Requires-Dist: pywt; extra == "ses"
+Requires-Dist: PyWavelets; extra == "ses"
 Provides-Extra: nexusgen
 Requires-Dist: qwen_vl_utils; extra == "nexusgen"
 Requires-Dist: transformers==4.49.0; extra == "nexusgen"
@@ -114,6 +114,12 @@ See also:
 
 > Currently, the development personnel of this project are limited, with most of the work handled by [Artiprocher](https://github.com/Artiprocher) and [mi804](https://github.com/mi804). Therefore, the progress of new feature development will be relatively slow, and the speed of responding to and resolving issues is limited. We apologize for this and ask developers to understand.
 
+- **October 20, 2026** We now support MOSS-Image, including inference and training for [MOSS-Image-Base](https://modelscope.cn/models/openmoss/MOSS-Image-Base) and [MOSS-Image-SFT](https://modelscope.cn/models/openmoss/MOSS-Image-SFT). In addition, we provide an [EntroPack low-bit quantized model](https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-EntroPack), which can run the 3.5-bit quantized model with as little as 4 GB of VRAM; and an [accelerated model](https://modelscope.cn/models/DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA) distillation-accelerated via [OPD training](https://diffsynth-studio-doc.readthedocs.io/en/latest/Training/Distillation.html), supporting 8-step ultra-fast inference.
+
+- **October 16, 2026** flux-3-image-klein open-sourced, welcome a new member to the image model family! Support includes text-to-image generation, multi-reference editing, layout control, low VRAM inference, and Base training capabilities. For details, please refer to the [documentation](/docs/en/Model_Details/FLUX.3.md) and [example code](/examples/flux3/). We quantized the model with [EntroPack](https://github.com/modelscope/entropack), providing pre-quantized models in 3-bit, 4-bit, and 6-bit versions at [DiffSynth-Studio/flux-3-image-klein-entropack](https://www.modelscope.cn/models/DiffSynth-Studio/flux-3-image-klein-entropack).
+
+- **October 12, 2026** We now support distillation accelerated training based on OPD (On-Policy Distillation), which enables distillation acceleration of models at an extremely low cost. For details, please refer to [Distillation Accelerated Training](/docs/en/Training/Distillation.md).
+
 - **September 29, 2026** We are excited to open-source EntroPack, a general-purpose tensor compression library for PyTorch that provides lossless compression with exact recovery and rate-controlled lossy compression, with GPU encoding and decoding. It is integrated into DiffSynth-Studio as a quantization backend, compressing model weights at arbitrary target bitrates in both inference and LoRA training. For more information, please refer to:
 
   * Project Page: https://github.com/modelscope/entropack
@@ -408,6 +414,8 @@ Quick start: experience popular and the latest models:
 Model overview:
 
 - Image generation
+    - MOSS-Image: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/MOSS-Image.html), [Example code](/examples/moss_image/)
+    - FLUX.3: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/FLUX.3.html), [Example code](/examples/flux3/)
     - Qwen-Image-2.1: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/Qwen-Image-2.1.html), [Example code](/examples/qwen_image_21/)
     - SenseNova-U1: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/SenseNova-U1.html), [Example code](/examples/sensenova_u1/)
     - Boogu-Image: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/Boogu-Image.html), [Example code](/examples/boogu_image/)
@@ -441,6 +449,21 @@ Model overview:
 
 We believe that a well-developed open-source code framework can lower the threshold for technical exploration. We have achieved many interesting technologies based on this codebase. Perhaps you also have many wild ideas, and with DiffSynth-Studio, you can quickly realize these ideas.
 
+<details>
+
+<summary>EntroPack: A General-Purpose Tensor Compression Library for PyTorch</summary>
+
+> Compress model weights at arbitrary target bitrates with GPU encoding and decoding, and run the compressed weights directly in inference and LoRA training.
+
+* Project Page: [GitHub](https://github.com/modelscope/entropack)
+* Technical Report: https://arxiv.org/abs/2609.34185
+* Pre-quantized Models: [ModelScope](https://www.modelscope.cn/models/DiffSynth-Studio/EntroPackPreQuants)
+* Documentation: [English Version](/docs/en/Pipeline_Usage/Quantization.md) | [Chinese Version](/docs/zh/Pipeline_Usage/Quantization.md)
+* Example Code: [Z-Image-Turbo](/examples/z_image/model_inference_low_vram/Z-Image-Turbo-EntroPack.py), [Qwen-Image-2.1](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1-EntroPack.py), [MiniMax-H3](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-EntroPack.py), [LoRA Training Example](/examples/z_image/model_training/special/quant_training/Z-Image-Turbo-entropack_lossy_quant.sh)
+
+</details>
+
+
 <details>
 
 <summary>TreeAdapter: A Model System Built from Structured LoRAs</summary>
@@ -679,6 +702,12 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 
 | Architecture | Model ID | Inference | Low VRAM Inference | Full Training | Validation After Full Training | LoRA Training | Validation After LoRA Training |
 |-|-|-|-|-|-|-|-|
+| MOSS-Image | [openmoss/MOSS-Image-Base](https://www.modelscope.cn/models/openmoss/MOSS-Image-Base) | [code](/examples/moss_image/model_inference/MOSS-Image-Base.py) | [code](/examples/moss_image/model_inference_low_vram/MOSS-Image-Base.py) | [code](/examples/moss_image/model_training/full/MOSS-Image-Base.sh) | [code](/examples/moss_image/model_training/validate_full/MOSS-Image-Base.py) | [code](/examples/moss_image/model_training/lora/MOSS-Image-Base.sh) | [code](/examples/moss_image/model_training/validate_lora/MOSS-Image-Base.py) |
+| MOSS-Image | [openmoss/MOSS-Image-SFT](https://www.modelscope.cn/models/openmoss/MOSS-Image-SFT) | [code](/examples/moss_image/model_inference/MOSS-Image-SFT.py) | [code](/examples/moss_image/model_inference_low_vram/MOSS-Image-SFT.py) | [code](/examples/moss_image/model_training/full/MOSS-Image-SFT.sh) | [code](/examples/moss_image/model_training/validate_full/MOSS-Image-SFT.py) | [code](/examples/moss_image/model_training/lora/MOSS-Image-SFT.sh) | [code](/examples/moss_image/model_training/validate_lora/MOSS-Image-SFT.py) |
+| MOSS-Image | [DiffSynth-Studio/MOSS-Image-EntroPack](https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-EntroPack) | [code](/examples/moss_image/model_inference/MOSS-Image-EntroPack.py) | [code](/examples/moss_image/model_inference_low_vram/MOSS-Image-EntroPack.py) | - | - | [code](/examples/moss_image/model_training/lora/MOSS-Image-entropack.sh) | [code](/examples/moss_image/model_training/validate_lora/MOSS-Image-entropack.py) |
+| FLUX.3 | [black-forest-labs/flux-3-image-klein](https://www.modelscope.cn/models/black-forest-labs/flux-3-image-klein) | [code](/examples/flux3/model_inference/flux-3-image-klein.py) | [code](/examples/flux3/model_inference_low_vram/flux-3-image-klein.py) | [code](/examples/flux3/model_training/full/flux-3-image-klein.sh) | [code](/examples/flux3/model_training/validate_full/flux-3-image-klein.py) | [code](/examples/flux3/model_training/lora/flux-3-image-klein.sh) | [code](/examples/flux3/model_training/validate_lora/flux-3-image-klein.py) |
+| FLUX.3 | [black-forest-labs/flux-3-image-klein-base](https://www.modelscope.cn/models/black-forest-labs/flux-3-image-klein-base) | [code](/examples/flux3/model_inference/flux-3-image-klein-base.py) | [code](/examples/flux3/model_inference_low_vram/flux-3-image-klein-base.py) | [code](/examples/flux3/model_training/full/flux-3-image-klein-base.sh) | [code](/examples/flux3/model_training/validate_full/flux-3-image-klein-base.py) | [code](/examples/flux3/model_training/lora/flux-3-image-klein-base.sh) | [code](/examples/flux3/model_training/validate_lora/flux-3-image-klein-base.py) |
+| FLUX.3 | [DiffSynth-Studio/flux-3-image-klein-entropack](https://www.modelscope.cn/models/DiffSynth-Studio/flux-3-image-klein-entropack) | [code](/examples/flux3/model_inference/flux-3-image-klein-EntroPack.py) | [code](/examples/flux3/model_inference_low_vram/flux-3-image-klein-EntroPack.py) | - | - | [code](/examples/flux3/model_training/lora/flux-3-image-klein-entropack.sh) | [code](/examples/flux3/model_training/validate_lora/flux-3-image-klein-entropack.py) |
 | Qwen-Image-2.1 | [Qwen/Qwen-Image-2.1](https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1) | [code](/examples/qwen_image_21/model_inference/Qwen-Image-2.1.py) | [code](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1.py) | [code](/examples/qwen_image_21/model_training/full/Qwen-Image-2.1.sh) | [code](/examples/qwen_image_21/model_training/validate_full/Qwen-Image-2.1.py) | [code](/examples/qwen_image_21/model_training/lora/Qwen-Image-2.1.sh) | [code](/examples/qwen_image_21/model_training/validate_lora/Qwen-Image-2.1.py) |
 | Qwen-Image-2.1 | [Qwen/Qwen-Image-2.1-Turbo](https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1-Turbo) | [code](/examples/qwen_image_21/model_inference/Qwen-Image-2.1-Turbo.py) | [code](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1-Turbo.py) | [code](/examples/qwen_image_21/model_training/full/Qwen-Image-2.1-Turbo.sh) | [code](/examples/qwen_image_21/model_training/validate_full/Qwen-Image-2.1-Turbo.py) | [code](/examples/qwen_image_21/model_training/lora/Qwen-Image-2.1-Turbo.sh) | [code](/examples/qwen_image_21/model_training/validate_lora/Qwen-Image-2.1-Turbo.py) |
 | Qwen-Image-2.1 | [PAI/Qwen-Image-2.1-Fun-Controlnet-Union](https://www.modelscope.cn/models/PAI/Qwen-Image-2.1-Fun-Controlnet-Union) | [code](/examples/qwen_image_21/model_inference/Qwen-Image-2.1-Fun-Controlnet-Union.py) | [code](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1-Fun-Controlnet-Union.py) | [code](/examples/qwen_image_21/model_training/full/Qwen-Image-2.1-Fun-Controlnet-Union.sh) | [code](/examples/qwen_image_21/model_training/validate_full/Qwen-Image-2.1-Fun-Controlnet-Union.py) | [code](/examples/qwen_image_21/model_training/lora/Qwen-Image-2.1-Fun-Controlnet-Union.sh) | [code](/examples/qwen_image_21/model_training/validate_lora/Qwen-Image-2.1-Fun-Controlnet-Union.py) |
@@ -708,6 +737,10 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 | MiniMax-H3 | [lightx2v/Minimax-h3-Turbo: FL2VA 4steps](https://www.modelscope.cn/models/lightx2v/Minimax-h3-Turbo) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/minimax_h3/model_inference/MiniMax-H3-FL2VA-Turbo.py) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-FL2VA-Turbo.py) | - | - | - | - |
 | MiniMax-H3 | [DiffSynth-Studio/MiniMax-H3-Text-Embeddings](https://www.modelscope.cn/models/DiffSynth-Studio/MiniMax-H3-Text-Embeddings) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-Text-Embeddings.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-Text-Embeddings.py) | [code](/examples/minimax_h3/model_training/full/MiniMax-H3-Text-Embeddings.sh) | [code](/examples/minimax_h3/model_training/validate_full/MiniMax-H3-Text-Embeddings.py) | - | - |
 | MiniMax-H3 | [PAI/MiniMax-H3-Fun-Controlnet-Union](https://www.modelscope.cn/models/PAI/MiniMax-H3-Fun-Controlnet-Union) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-Fun-Controlnet-Union.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-Fun-Controlnet-Union.py) | [code](/examples/minimax_h3/model_training/full/MiniMax-H3-Fun-Controlnet-Union.sh) | [code](/examples/minimax_h3/model_training/validate_full/MiniMax-H3-Fun-Controlnet-Union.py) | [code](/examples/minimax_h3/model_training/lora/MiniMax-H3-Fun-Controlnet-Union.sh) | [code](/examples/minimax_h3/model_training/validate_lora/MiniMax-H3-Fun-Controlnet-Union.py) |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 50 steps](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-FL2VA.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-VDN-FL2VA.py) | - | - | - | - |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 8 steps](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-Turbo-FL2VA.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-VDN-Turbo-FL2VA.py) | - | - | - | - |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 FP8](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-FP8-FL2VA.py) | - | - | - | - | - |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 8 steps FP8](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-Turbo-FP8-FL2VA.py) | - | - | - | - | - |
 | LingBot-Video | [Robbyant/lingbot-video-dense-1.3b: T2V](https://modelscope.cn/models/Robbyant/lingbot-video-dense-1.3b) | [code](/examples/lingbot_video/model_inference/lingbot-video-dense-1.3b_t2v.py) | [code](/examples/lingbot_video/model_inference_low_vram/lingbot-video-dense-1.3b_t2v.py) | [code](/examples/lingbot_video/model_training/full/lingbot-video-dense-1.3b_t2v.sh) | [code](/examples/lingbot_video/model_training/validate_full/lingbot-video-dense-1.3b_t2v.py) | [code](/examples/lingbot_video/model_training/lora/lingbot-video-dense-1.3b_t2v.sh) | [code](/examples/lingbot_video/model_training/validate_lora/lingbot-video-dense-1.3b_t2v.py) |
 | LingBot-Video | [Robbyant/lingbot-video-dense-1.3b: TI2V](https://modelscope.cn/models/Robbyant/lingbot-video-dense-1.3b) | [code](/examples/lingbot_video/model_inference/lingbot-video-dense-1.3b_ti2v.py) | [code](/examples/lingbot_video/model_inference_low_vram/lingbot-video-dense-1.3b_ti2v.py) | [code](/examples/lingbot_video/model_training/full/lingbot-video-dense-1.3b_ti2v.sh) | [code](/examples/lingbot_video/model_training/validate_full/lingbot-video-dense-1.3b_ti2v.py) | [code](/examples/lingbot_video/model_training/lora/lingbot-video-dense-1.3b_ti2v.sh) | [code](/examples/lingbot_video/model_training/validate_lora/lingbot-video-dense-1.3b_ti2v.py) |
 | LingBot-Video | [Robbyant/lingbot-video-dense-1.3b: T2I](https://modelscope.cn/models/Robbyant/lingbot-video-dense-1.3b) | [code](/examples/lingbot_video/model_inference/lingbot-video-dense-1.3b_t2i.py) | [code](/examples/lingbot_video/model_inference_low_vram/lingbot-video-dense-1.3b_t2i.py) | - | - | - | - |
@@ -750,7 +783,7 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 | LTX-2.5 | [Lightricks/LTX-2.5: T2A](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2A.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2A.py) | - | - | - | - |
 | LTX-2.5 | [Lightricks/LTX-2.5: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2AV-DistilledPipeline.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2AV-DistilledPipeline.py) | - | - | - | - |
 | LTX-2.5 | [Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler](https://www.modelscope.cn/models/Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler) | [code](/examples/ltx2/model_inference/LTX-2.5-IC-LoRA-Pixel-Spatial-Upscaler.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-IC-LoRA-Pixel-Spatial-Upscaler.py) | - | - | - | - |
-| LTX-2.5 | [Lightricks/LTX-2.5: INT8-ConvRot](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2AV-INT8-ConvRot.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2AV-INT8-ConvRot.py) | - | - | - | - |
+| LTX-2.5 | [Lightricks/LTX-2.5: INT8-ConvRot](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2AV-INT8-ConvRot.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2AV-INT8-ConvRot.py) | - | - | [code](/examples/ltx2/model_training/lora/LTX-2.5-Int8-ConvRot-splited.sh) | [code](/examples/ltx2/model_training/validate_lora/LTX-2.5-Int8-ConvRot.py) |
 | LTX-2 | [jd-opensource/JoyAI-Echo](https://modelscope.cn/models/jd-opensource/JoyAI-Echo) | [code](/examples/ltx2/model_inference/JoyAI-Echo-T2AV.py) | [code](/examples/ltx2/model_inference_low_vram/JoyAI-Echo-T2AV.py) | [code](/examples/ltx2/model_training/full/JoyAI-Echo-T2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_full/JoyAI-Echo-T2AV.py) | [code](/examples/ltx2/model_training/lora/JoyAI-Echo-T2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_lora/JoyAI-Echo-T2AV.py) |
 | LTX-2 | [Lightricks/LTX-2.3: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3) | [code](/examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py) | [code](/examples/ltx2/model_training/full/LTX-2.3-I2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_full/LTX-2.3-I2AV.py) | [code](/examples/ltx2/model_training/lora/LTX-2.3-I2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_lora/LTX-2.3-I2AV.py) |
 | LTX-2 | [Lightricks/LTX-2.3: TwoStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3) | [code](/examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py) | - | - | - | - |

{diffsynth-2.1.9 → diffsynth-2.1.10}/README.md

@@ -41,6 +41,12 @@ See also:
 
 > Currently, the development personnel of this project are limited, with most of the work handled by [Artiprocher](https://github.com/Artiprocher) and [mi804](https://github.com/mi804). Therefore, the progress of new feature development will be relatively slow, and the speed of responding to and resolving issues is limited. We apologize for this and ask developers to understand.
 
+- **October 20, 2026** We now support MOSS-Image, including inference and training for [MOSS-Image-Base](https://modelscope.cn/models/openmoss/MOSS-Image-Base) and [MOSS-Image-SFT](https://modelscope.cn/models/openmoss/MOSS-Image-SFT). In addition, we provide an [EntroPack low-bit quantized model](https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-EntroPack), which can run the 3.5-bit quantized model with as little as 4 GB of VRAM; and an [accelerated model](https://modelscope.cn/models/DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA) distillation-accelerated via [OPD training](https://diffsynth-studio-doc.readthedocs.io/en/latest/Training/Distillation.html), supporting 8-step ultra-fast inference.
+
+- **October 16, 2026** flux-3-image-klein open-sourced, welcome a new member to the image model family! Support includes text-to-image generation, multi-reference editing, layout control, low VRAM inference, and Base training capabilities. For details, please refer to the [documentation](/docs/en/Model_Details/FLUX.3.md) and [example code](/examples/flux3/). We quantized the model with [EntroPack](https://github.com/modelscope/entropack), providing pre-quantized models in 3-bit, 4-bit, and 6-bit versions at [DiffSynth-Studio/flux-3-image-klein-entropack](https://www.modelscope.cn/models/DiffSynth-Studio/flux-3-image-klein-entropack).
+
+- **October 12, 2026** We now support distillation accelerated training based on OPD (On-Policy Distillation), which enables distillation acceleration of models at an extremely low cost. For details, please refer to [Distillation Accelerated Training](/docs/en/Training/Distillation.md).
+
 - **September 29, 2026** We are excited to open-source EntroPack, a general-purpose tensor compression library for PyTorch that provides lossless compression with exact recovery and rate-controlled lossy compression, with GPU encoding and decoding. It is integrated into DiffSynth-Studio as a quantization backend, compressing model weights at arbitrary target bitrates in both inference and LoRA training. For more information, please refer to:
 
   * Project Page: https://github.com/modelscope/entropack
@@ -335,6 +341,8 @@ Quick start: experience popular and the latest models:
 Model overview:
 
 - Image generation
+    - MOSS-Image: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/MOSS-Image.html), [Example code](/examples/moss_image/)
+    - FLUX.3: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/FLUX.3.html), [Example code](/examples/flux3/)
     - Qwen-Image-2.1: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/Qwen-Image-2.1.html), [Example code](/examples/qwen_image_21/)
     - SenseNova-U1: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/SenseNova-U1.html), [Example code](/examples/sensenova_u1/)
     - Boogu-Image: [Documentation](https://diffsynth-studio-doc.readthedocs.io/en/latest/Model_Details/Boogu-Image.html), [Example code](/examples/boogu_image/)
@@ -368,6 +376,21 @@ Model overview:
 
 We believe that a well-developed open-source code framework can lower the threshold for technical exploration. We have achieved many interesting technologies based on this codebase. Perhaps you also have many wild ideas, and with DiffSynth-Studio, you can quickly realize these ideas.
 
+<details>
+
+<summary>EntroPack: A General-Purpose Tensor Compression Library for PyTorch</summary>
+
+> Compress model weights at arbitrary target bitrates with GPU encoding and decoding, and run the compressed weights directly in inference and LoRA training.
+
+* Project Page: [GitHub](https://github.com/modelscope/entropack)
+* Technical Report: https://arxiv.org/abs/2609.34185
+* Pre-quantized Models: [ModelScope](https://www.modelscope.cn/models/DiffSynth-Studio/EntroPackPreQuants)
+* Documentation: [English Version](/docs/en/Pipeline_Usage/Quantization.md) | [Chinese Version](/docs/zh/Pipeline_Usage/Quantization.md)
+* Example Code: [Z-Image-Turbo](/examples/z_image/model_inference_low_vram/Z-Image-Turbo-EntroPack.py), [Qwen-Image-2.1](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1-EntroPack.py), [MiniMax-H3](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-EntroPack.py), [LoRA Training Example](/examples/z_image/model_training/special/quant_training/Z-Image-Turbo-entropack_lossy_quant.sh)
+
+</details>
+
+
 <details>
 
 <summary>TreeAdapter: A Model System Built from Structured LoRAs</summary>
@@ -606,6 +629,12 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 
 | Architecture | Model ID | Inference | Low VRAM Inference | Full Training | Validation After Full Training | LoRA Training | Validation After LoRA Training |
 |-|-|-|-|-|-|-|-|
+| MOSS-Image | [openmoss/MOSS-Image-Base](https://www.modelscope.cn/models/openmoss/MOSS-Image-Base) | [code](/examples/moss_image/model_inference/MOSS-Image-Base.py) | [code](/examples/moss_image/model_inference_low_vram/MOSS-Image-Base.py) | [code](/examples/moss_image/model_training/full/MOSS-Image-Base.sh) | [code](/examples/moss_image/model_training/validate_full/MOSS-Image-Base.py) | [code](/examples/moss_image/model_training/lora/MOSS-Image-Base.sh) | [code](/examples/moss_image/model_training/validate_lora/MOSS-Image-Base.py) |
+| MOSS-Image | [openmoss/MOSS-Image-SFT](https://www.modelscope.cn/models/openmoss/MOSS-Image-SFT) | [code](/examples/moss_image/model_inference/MOSS-Image-SFT.py) | [code](/examples/moss_image/model_inference_low_vram/MOSS-Image-SFT.py) | [code](/examples/moss_image/model_training/full/MOSS-Image-SFT.sh) | [code](/examples/moss_image/model_training/validate_full/MOSS-Image-SFT.py) | [code](/examples/moss_image/model_training/lora/MOSS-Image-SFT.sh) | [code](/examples/moss_image/model_training/validate_lora/MOSS-Image-SFT.py) |
+| MOSS-Image | [DiffSynth-Studio/MOSS-Image-EntroPack](https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-EntroPack) | [code](/examples/moss_image/model_inference/MOSS-Image-EntroPack.py) | [code](/examples/moss_image/model_inference_low_vram/MOSS-Image-EntroPack.py) | - | - | [code](/examples/moss_image/model_training/lora/MOSS-Image-entropack.sh) | [code](/examples/moss_image/model_training/validate_lora/MOSS-Image-entropack.py) |
+| FLUX.3 | [black-forest-labs/flux-3-image-klein](https://www.modelscope.cn/models/black-forest-labs/flux-3-image-klein) | [code](/examples/flux3/model_inference/flux-3-image-klein.py) | [code](/examples/flux3/model_inference_low_vram/flux-3-image-klein.py) | [code](/examples/flux3/model_training/full/flux-3-image-klein.sh) | [code](/examples/flux3/model_training/validate_full/flux-3-image-klein.py) | [code](/examples/flux3/model_training/lora/flux-3-image-klein.sh) | [code](/examples/flux3/model_training/validate_lora/flux-3-image-klein.py) |
+| FLUX.3 | [black-forest-labs/flux-3-image-klein-base](https://www.modelscope.cn/models/black-forest-labs/flux-3-image-klein-base) | [code](/examples/flux3/model_inference/flux-3-image-klein-base.py) | [code](/examples/flux3/model_inference_low_vram/flux-3-image-klein-base.py) | [code](/examples/flux3/model_training/full/flux-3-image-klein-base.sh) | [code](/examples/flux3/model_training/validate_full/flux-3-image-klein-base.py) | [code](/examples/flux3/model_training/lora/flux-3-image-klein-base.sh) | [code](/examples/flux3/model_training/validate_lora/flux-3-image-klein-base.py) |
+| FLUX.3 | [DiffSynth-Studio/flux-3-image-klein-entropack](https://www.modelscope.cn/models/DiffSynth-Studio/flux-3-image-klein-entropack) | [code](/examples/flux3/model_inference/flux-3-image-klein-EntroPack.py) | [code](/examples/flux3/model_inference_low_vram/flux-3-image-klein-EntroPack.py) | - | - | [code](/examples/flux3/model_training/lora/flux-3-image-klein-entropack.sh) | [code](/examples/flux3/model_training/validate_lora/flux-3-image-klein-entropack.py) |
 | Qwen-Image-2.1 | [Qwen/Qwen-Image-2.1](https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1) | [code](/examples/qwen_image_21/model_inference/Qwen-Image-2.1.py) | [code](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1.py) | [code](/examples/qwen_image_21/model_training/full/Qwen-Image-2.1.sh) | [code](/examples/qwen_image_21/model_training/validate_full/Qwen-Image-2.1.py) | [code](/examples/qwen_image_21/model_training/lora/Qwen-Image-2.1.sh) | [code](/examples/qwen_image_21/model_training/validate_lora/Qwen-Image-2.1.py) |
 | Qwen-Image-2.1 | [Qwen/Qwen-Image-2.1-Turbo](https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1-Turbo) | [code](/examples/qwen_image_21/model_inference/Qwen-Image-2.1-Turbo.py) | [code](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1-Turbo.py) | [code](/examples/qwen_image_21/model_training/full/Qwen-Image-2.1-Turbo.sh) | [code](/examples/qwen_image_21/model_training/validate_full/Qwen-Image-2.1-Turbo.py) | [code](/examples/qwen_image_21/model_training/lora/Qwen-Image-2.1-Turbo.sh) | [code](/examples/qwen_image_21/model_training/validate_lora/Qwen-Image-2.1-Turbo.py) |
 | Qwen-Image-2.1 | [PAI/Qwen-Image-2.1-Fun-Controlnet-Union](https://www.modelscope.cn/models/PAI/Qwen-Image-2.1-Fun-Controlnet-Union) | [code](/examples/qwen_image_21/model_inference/Qwen-Image-2.1-Fun-Controlnet-Union.py) | [code](/examples/qwen_image_21/model_inference_low_vram/Qwen-Image-2.1-Fun-Controlnet-Union.py) | [code](/examples/qwen_image_21/model_training/full/Qwen-Image-2.1-Fun-Controlnet-Union.sh) | [code](/examples/qwen_image_21/model_training/validate_full/Qwen-Image-2.1-Fun-Controlnet-Union.py) | [code](/examples/qwen_image_21/model_training/lora/Qwen-Image-2.1-Fun-Controlnet-Union.sh) | [code](/examples/qwen_image_21/model_training/validate_lora/Qwen-Image-2.1-Fun-Controlnet-Union.py) |
@@ -635,6 +664,10 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 | MiniMax-H3 | [lightx2v/Minimax-h3-Turbo: FL2VA 4steps](https://www.modelscope.cn/models/lightx2v/Minimax-h3-Turbo) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/minimax_h3/model_inference/MiniMax-H3-FL2VA-Turbo.py) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-FL2VA-Turbo.py) | - | - | - | - |
 | MiniMax-H3 | [DiffSynth-Studio/MiniMax-H3-Text-Embeddings](https://www.modelscope.cn/models/DiffSynth-Studio/MiniMax-H3-Text-Embeddings) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-Text-Embeddings.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-Text-Embeddings.py) | [code](/examples/minimax_h3/model_training/full/MiniMax-H3-Text-Embeddings.sh) | [code](/examples/minimax_h3/model_training/validate_full/MiniMax-H3-Text-Embeddings.py) | - | - |
 | MiniMax-H3 | [PAI/MiniMax-H3-Fun-Controlnet-Union](https://www.modelscope.cn/models/PAI/MiniMax-H3-Fun-Controlnet-Union) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-Fun-Controlnet-Union.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-Fun-Controlnet-Union.py) | [code](/examples/minimax_h3/model_training/full/MiniMax-H3-Fun-Controlnet-Union.sh) | [code](/examples/minimax_h3/model_training/validate_full/MiniMax-H3-Fun-Controlnet-Union.py) | [code](/examples/minimax_h3/model_training/lora/MiniMax-H3-Fun-Controlnet-Union.sh) | [code](/examples/minimax_h3/model_training/validate_lora/MiniMax-H3-Fun-Controlnet-Union.py) |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 50 steps](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-FL2VA.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-VDN-FL2VA.py) | - | - | - | - |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 8 steps](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-Turbo-FL2VA.py) | [code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-VDN-Turbo-FL2VA.py) | - | - | - | - |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 FP8](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-FP8-FL2VA.py) | - | - | - | - | - |
+| MiniMax-H3 | [OpenVDN/vdn-minimax-h3: VDN-H3 8 steps FP8](https://www.modelscope.cn/models/OpenVDN/vdn-minimax-h3) | [code](/examples/minimax_h3/model_inference/MiniMax-H3-VDN-Turbo-FP8-FL2VA.py) | - | - | - | - | - |
 | LingBot-Video | [Robbyant/lingbot-video-dense-1.3b: T2V](https://modelscope.cn/models/Robbyant/lingbot-video-dense-1.3b) | [code](/examples/lingbot_video/model_inference/lingbot-video-dense-1.3b_t2v.py) | [code](/examples/lingbot_video/model_inference_low_vram/lingbot-video-dense-1.3b_t2v.py) | [code](/examples/lingbot_video/model_training/full/lingbot-video-dense-1.3b_t2v.sh) | [code](/examples/lingbot_video/model_training/validate_full/lingbot-video-dense-1.3b_t2v.py) | [code](/examples/lingbot_video/model_training/lora/lingbot-video-dense-1.3b_t2v.sh) | [code](/examples/lingbot_video/model_training/validate_lora/lingbot-video-dense-1.3b_t2v.py) |
 | LingBot-Video | [Robbyant/lingbot-video-dense-1.3b: TI2V](https://modelscope.cn/models/Robbyant/lingbot-video-dense-1.3b) | [code](/examples/lingbot_video/model_inference/lingbot-video-dense-1.3b_ti2v.py) | [code](/examples/lingbot_video/model_inference_low_vram/lingbot-video-dense-1.3b_ti2v.py) | [code](/examples/lingbot_video/model_training/full/lingbot-video-dense-1.3b_ti2v.sh) | [code](/examples/lingbot_video/model_training/validate_full/lingbot-video-dense-1.3b_ti2v.py) | [code](/examples/lingbot_video/model_training/lora/lingbot-video-dense-1.3b_ti2v.sh) | [code](/examples/lingbot_video/model_training/validate_lora/lingbot-video-dense-1.3b_ti2v.py) |
 | LingBot-Video | [Robbyant/lingbot-video-dense-1.3b: T2I](https://modelscope.cn/models/Robbyant/lingbot-video-dense-1.3b) | [code](/examples/lingbot_video/model_inference/lingbot-video-dense-1.3b_t2i.py) | [code](/examples/lingbot_video/model_inference_low_vram/lingbot-video-dense-1.3b_t2i.py) | - | - | - | - |
@@ -677,7 +710,7 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 | LTX-2.5 | [Lightricks/LTX-2.5: T2A](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2A.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2A.py) | - | - | - | - |
 | LTX-2.5 | [Lightricks/LTX-2.5: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2AV-DistilledPipeline.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2AV-DistilledPipeline.py) | - | - | - | - |
 | LTX-2.5 | [Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler](https://www.modelscope.cn/models/Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler) | [code](/examples/ltx2/model_inference/LTX-2.5-IC-LoRA-Pixel-Spatial-Upscaler.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-IC-LoRA-Pixel-Spatial-Upscaler.py) | - | - | - | - |
-| LTX-2.5 | [Lightricks/LTX-2.5: INT8-ConvRot](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2AV-INT8-ConvRot.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2AV-INT8-ConvRot.py) | - | - | - | - |
+| LTX-2.5 | [Lightricks/LTX-2.5: INT8-ConvRot](https://www.modelscope.cn/models/Lightricks/LTX-2.5) | [code](/examples/ltx2/model_inference/LTX-2.5-T2AV-INT8-ConvRot.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.5-T2AV-INT8-ConvRot.py) | - | - | [code](/examples/ltx2/model_training/lora/LTX-2.5-Int8-ConvRot-splited.sh) | [code](/examples/ltx2/model_training/validate_lora/LTX-2.5-Int8-ConvRot.py) |
 | LTX-2 | [jd-opensource/JoyAI-Echo](https://modelscope.cn/models/jd-opensource/JoyAI-Echo) | [code](/examples/ltx2/model_inference/JoyAI-Echo-T2AV.py) | [code](/examples/ltx2/model_inference_low_vram/JoyAI-Echo-T2AV.py) | [code](/examples/ltx2/model_training/full/JoyAI-Echo-T2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_full/JoyAI-Echo-T2AV.py) | [code](/examples/ltx2/model_training/lora/JoyAI-Echo-T2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_lora/JoyAI-Echo-T2AV.py) |
 | LTX-2 | [Lightricks/LTX-2.3: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3) | [code](/examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py) | [code](/examples/ltx2/model_training/full/LTX-2.3-I2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_full/LTX-2.3-I2AV.py) | [code](/examples/ltx2/model_training/lora/LTX-2.3-I2AV-splited.sh) | [code](/examples/ltx2/model_training/validate_lora/LTX-2.3-I2AV.py) |
 | LTX-2 | [Lightricks/LTX-2.3: TwoStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3) | [code](/examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py) | [code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py) | - | - | - | - |

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/configs/model_configs.py

@@ -605,6 +605,53 @@ ernie_image_series = [
     },
 ]
 
+moss_image_series = [
+    {
+        # Example: ModelConfig(model_id="openmoss/MOSS-Image-Base", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
+        # Example: ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
+        "model_hash": "b2e1de16b1415bb811bcfc428d7991a7",
+        "model_name": "moss_image_dit",
+        "model_class": "diffsynth.models.moss_image_dit.MOSSImageDiT",
+    },
+    {
+        # Example: ModelConfig(model_id="openmoss/MOSS-Image-Base", origin_file_pattern="text_encoder/model*.safetensors")
+        # Example: ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="text_encoder/model*.safetensors")
+        "model_hash": "a7140be40b65f94f31942d5b5225f781",
+        "model_name": "moss_image_text_encoder",
+        "model_class": "diffsynth.models.moss_image_text_encoder.MOSSImageTextEncoder",
+        "state_dict_converter": "diffsynth.utils.state_dict_converters.moss_image_text_encoder.MOSSImageTextEncoderStateDictConverter",
+    },
+    {
+        # Example: ModelConfig(model_id="openmoss/MOSS-Image-Base", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
+        # Example: ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
+        "model_hash": "dc89b5bac72b57182f384e21632db90d",
+        "model_name": "flux2_vae",
+        "model_class": "diffsynth.models.flux2_vae.Flux2VAE",
+        "extra_kwargs": {"decoder_block_out_channels": [96, 192, 384, 384]}
+    },
+    {
+        # Example: ModelConfig(model_id="DiffSynth-Studio/MOSS-Image-EntroPack", origin_file_pattern="models/MOSS-Image-Base/dit_6bit.safetensors")
+        "model_hash": "b895b1ad67dd7a9f225dc4ad7dcec3f2",
+        "model_name": "moss_image_dit",
+        "model_class": "diffsynth.models.moss_image_dit.MOSSImageDiT",
+        "quant_config": {"method": "entropack_lossy_quant", "load_prequantized": True, "backend_config_kwargs": {"target_bpp": 6.0, "row_rdo_iterations": 2, "row_rdo_candidates": 20}},
+    },
+    {
+        # Example: ModelConfig(model_id="DiffSynth-Studio/MOSS-Image-EntroPack", origin_file_pattern="models/MOSS-Image-SFT/dit_6bit.safetensors")
+        "model_hash": "6f2e6e215ce1ad45e42ef84632165fbd",
+        "model_name": "moss_image_dit",
+        "model_class": "diffsynth.models.moss_image_dit.MOSSImageDiT",
+        "quant_config": {"method": "entropack_lossy_quant", "load_prequantized": True, "backend_config_kwargs": {"target_bpp": 6.0, "row_rdo_iterations": 2, "row_rdo_candidates": 20}},
+    },
+    {
+        # Example: ModelConfig(model_id="DiffSynth-Studio/MOSS-Image-EntroPack", origin_file_pattern="models/text_encoder_6bit.safetensors")
+        "model_hash": "c857c646d678fc7f40fe8465524efeeb",
+        "model_name": "moss_image_text_encoder",
+        "model_class": "diffsynth.models.moss_image_text_encoder.MOSSImageTextEncoder",
+        "quant_config": {"method": "entropack_lossy_quant", "load_prequantized": True, "backend_config_kwargs": {"target_bpp": 6.0, "row_rdo_iterations": 2, "row_rdo_candidates": 20}},
+    },
+]
+
 z_image_series = [
     {
         # Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors")
@@ -1653,6 +1700,13 @@ minimax_h3_series = [
         "quant_config": {"method": "comfy_kitchen_int8_w8a8", "load_prequantized": True, "exclude_modules": ["video_patch_proj", "audio_patch_proj", "condition_proj", "time_embedder.proj_in", "time_embedder.proj_out", "final_layer.adaln_proj.linear", "final_layer.video_out", "final_layer.audio_out", "token_refiner.blocks.0.attn.qkv_proj", "token_refiner.blocks.0.attn.out_proj", "token_refiner.blocks.0.mlp.fc1", "token_refiner.blocks.0.mlp.fc2", "token_refiner.blocks.1.attn.qkv_proj", "token_refiner.blocks.1.attn.out_proj", "token_refiner.blocks.1.mlp.fc1", "token_refiner.blocks.1.mlp.fc2"]},
         "state_dict_converter": "diffsynth.utils.state_dict_converters.minimax_h3_dit.MiniMaxH3DiTSingularityStateDictConverter",
     },
+    {
+        # Example: ModelConfig(model_id="OpenVDN/vdn-minimax-h3", origin_file_pattern="stage-dmd-step-250/linear_branch/model.safetensors")
+        "model_hash": "6b8d2b6ae09fc45cbe3e5a9a57e4512a",
+        "model_name": "minimax_h3_vdn_linear_branch",
+        "model_class": "diffsynth.models.minimax_h3_dit_vdn.MiniMaxH3VDNBranch",
+        "state_dict_converter": "diffsynth.utils.state_dict_converters.minimax_h3_dit_vdn.MiniMaxH3VDNBranchStateDictConverter",
+    },
 ]
 
 minimax_music3_series = [
@@ -1743,9 +1797,55 @@ qwen_image_21_series = [
     },
 ]
 
+flux3_series = [
+    {
+        # Example: ModelConfig(model_id="black-forest-labs/flux-3-image-klein", origin_file_pattern="model.safetensors")
+        "model_hash": "cb8e9c6df08faa5cf99c11be4d34d26b",
+        "model_name": "flux3_dit",
+        "model_class": "diffsynth.models.flux3_dit.Flux3DiT",
+        "extra_kwargs": {"flow_map": True},
+    },
+    {
+        # Example: ModelConfig(model_id="black-forest-labs/flux-3-image-klein", origin_file_pattern="transformer/*.safetensors")
+        "model_hash": "d98fcf51c088ad9910399b0d7fdfe692",
+        "model_name": "flux3_dit",
+        "model_class": "diffsynth.models.flux3_dit.Flux3DiTDiffusers",
+        "state_dict_converter": "diffsynth.utils.state_dict_converters.flux3_dit.Flux3DiTFromDiffusers",
+        "extra_kwargs": {"flow_map": True},
+    },
+    {
+        # Example: ModelConfig(model_id="black-forest-labs/flux-3-image-klein-base", origin_file_pattern="model.safetensors")
+        "model_hash": "3a12023223002ebc2f30c85d3d1257ea",
+        "model_name": "flux3_dit",
+        "model_class": "diffsynth.models.flux3_dit.Flux3DiT",
+    },
+    {
+        # Example: ModelConfig(model_id="black-forest-labs/flux-3-image-klein-base", origin_file_pattern="transformer/*.safetensors")
+        "model_hash": "fb4609249d89aeb716222378f92005ce",
+        "model_name": "flux3_dit",
+        "model_class": "diffsynth.models.flux3_dit.Flux3DiTDiffusers",
+        "state_dict_converter": "diffsynth.utils.state_dict_converters.flux3_dit.Flux3DiTFromDiffusers",
+    },
+    {
+        # Example: ModelConfig(model_id="DiffSynth-Studio/flux-3-image-klein-entropack", origin_file_pattern="models/dit_4bit.safetensors")
+        "model_hash": "3899702d86c8f8249bdb1535359c424b",
+        "model_name": "flux3_dit",
+        "model_class": "diffsynth.models.flux3_dit.Flux3DiT",
+        "extra_kwargs": {"flow_map": True},
+        "quant_config": {"method": "entropack_lossy_quant", "load_prequantized": True, "backend_config_kwargs": {"target_bpp": 4.0, "row_rdo_iterations": 2, "row_rdo_candidates": 20}},
+    },
+    {
+        # Example: ModelConfig(model_id="DiffSynth-Studio/flux-3-image-klein-entropack", origin_file_pattern="models/text_encoder_4bit.safetensors")
+        "model_hash": "05233849ee3764c2665a2165b5d4adff",
+        "model_name": "krea2_text_encoder",
+        "model_class": "diffsynth.models.krea2_text_encoder.Krea2TextEncoder",
+        "quant_config": {"method": "entropack_lossy_quant", "load_prequantized": True, "backend_config_kwargs": {"target_bpp": 4.0, "row_rdo_iterations": 2, "row_rdo_candidates": 20}},
+    },
+]
+
 MODEL_CONFIGS = (
     stable_diffusion_xl_series + stable_diffusion_series + qwen_image_series + qwen_video_edit_series + wan_series + flux_series + flux2_series + ernie_image_series
     + z_image_series + ltx2_series + anima_series + mova_series + joyai_image_series + boogu_image_series + ace_step_series + hidream_o1_image_series
     + image_metrics_series + ideogram4_series + krea2_series + lingbot_video_series + minimax_h3_series + minimax_music3_series + sensenova_u1_series
-    + yue2_series + qwen_image_21_series
+    + yue2_series + qwen_image_21_series + flux3_series + moss_image_series
 )

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/configs/vram_management_module_maps.py

@@ -22,6 +22,13 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
         "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
         "torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
     },
+    "diffsynth.models.minimax_h3_dit_vdn.MiniMaxH3VDNBranch": {
+        "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
+        "torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.minimax_h3_dit_vdn.MiniMaxH3VDNTemporalConv": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.minimax_h3_dit_vdn.MiniMaxH3VDNRMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.minimax_h3_dit_vdn.MiniMaxH3VDNAlpha": "diffsynth.core.vram.layers.AutoWrappedModule",
+    },
     "diffsynth.models.minimax_h3_text_encoder.MiniMaxH3TextEncoder": {
         "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
         "torch.nn.Embedding": "diffsynth.core.vram.layers.AutoWrappedModule",
@@ -234,6 +241,11 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
         "torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
         "torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
     },
+    "diffsynth.models.flux3_dit.Flux3DiT": {
+        "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
+        "diffsynth.models.flux3_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.flux3_dit.QKNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+    },
     "diffsynth.models.flux2_text_encoder.Flux2TextEncoder": {
         "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
         "torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
@@ -355,6 +367,19 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
         "torch.nn.Embedding": "diffsynth.core.vram.layers.AutoWrappedModule",
         "transformers.models.ministral3.modeling_ministral3.Ministral3RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
     },
+    "diffsynth.models.moss_image_dit.MOSSImageDiT": {
+        "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
+        "diffsynth.models.general_modules.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+    },
+    "diffsynth.models.moss_image_text_encoder.MOSSImageTextEncoder": {
+        "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
+        "torch.nn.Embedding": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "torch.nn.Conv1d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "transformers.models.qwen3_5.modeling_qwen3_5.Qwen3_5RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "transformers.models.qwen3_5.modeling_qwen3_5.Qwen3_5RMSNormGated": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "transformers.models.qwen3_5.modeling_qwen3_5.Qwen3_5TextRotaryEmbedding": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "transformers.models.qwen3_5.modeling_qwen3_5.Qwen3_5GatedDeltaNet": "diffsynth.core.vram.layers.AutoWrappedNonRecurseModule",
+    },
     "diffsynth.models.joyai_image_dit.JoyAIImageDiT": {
         "diffsynth.models.joyai_image_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
         "diffsynth.models.joyai_image_dit.ModulateWan": "diffsynth.core.vram.layers.AutoWrappedModule",

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/core/data/unified_dataset.py

@@ -61,7 +61,7 @@ class UnifiedDataset(torch.utils.data.Dataset):
         ])
         
     def search_for_cached_data_files(self, path):
-        for file_name in os.listdir(path):
+        for file_name in sorted(os.listdir(path)):
             subpath = os.path.join(path, file_name)
             if os.path.isdir(subpath):
                 self.search_for_cached_data_files(subpath)

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/core/gradient/gradient_checkpoint.py

@@ -14,9 +14,11 @@ def create_custom_forward(module):
     return custom_forward
 
 
-def create_custom_forward_use_reentrant(module):
+def create_custom_forward_use_reentrant(module, num_positional_args, kwarg_keys):
     def custom_forward(*inputs):
-        return module(*inputs)
+        positional_args = inputs[:num_positional_args]
+        keyword_args = dict(zip(kwarg_keys, inputs[num_positional_args:]))
+        return module(*positional_args, **keyword_args)
     return custom_forward
 
 
@@ -35,13 +37,18 @@ def gradient_checkpoint_forward(
     **kwargs,
 ):
     if use_gradient_checkpointing and _HAS_DEEPSPEED and deepspeed.checkpointing.is_configured():
+        kwarg_keys = tuple(kwargs)
         all_args = args + tuple(kwargs.values())
         if not judge_args_requires_grad(*all_args):
             # get the first grad_enabled tensor from un_checkpointed forward
             model_output = model(*args, **kwargs)
         else:
             model_output = deepspeed.checkpointing.checkpoint(
-                create_custom_forward_use_reentrant(model),
+                create_custom_forward_use_reentrant(
+                    model,
+                    len(args),
+                    kwarg_keys,
+                ),
                 *all_args,
             )
         return model_output

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/core/quant/backends/entropack.py

@@ -51,6 +51,11 @@ if ENTROPACK_AVAILABLE:
         linear_cls = ep.CompressedINT8Linear
 
 
+def _graph_break_quantized_linear(module):
+    module.forward = torch._dynamo.disable(module.forward)
+    return module
+
+
 @register_quant_backend("entropack")
 class EntroPackQuantBackend(QuantBackend):
     """Adapter over entropack's `CompressedLinear` family; a method's config is the config its layers get."""
@@ -70,7 +75,7 @@ class EntroPackQuantBackend(QuantBackend):
         return {
             "is_serializable": True,
             "is_differentiable": True,
-            "is_compileable": False,
+            "is_compileable": True,
             "requires_calibration": False,
         }
 
@@ -85,13 +90,15 @@ class EntroPackQuantBackend(QuantBackend):
         if compute_device is not None:
             linear = linear.to(device=compute_device)
         quantized = self.config.linear_cls.from_linear(linear, config=self.config)
-        return quantized if model_device is None else quantized.to(device=model_device)
+        quantized = quantized if model_device is None else quantized.to(device=model_device)
+        return _graph_break_quantized_linear(quantized)
 
     def create_quantized_linear_shell(self, linear, compute_dtype):
-        return self.config.linear_cls(
+        shell = self.config.linear_cls(
             linear.in_features, linear.out_features, bias=linear.bias is not None,
             dtype=compute_dtype, config=self.config,
         )
+        return _graph_break_quantized_linear(shell)
 
     def dequantize_to_linear(self, module, compute_dtype, compute_device=None, model_device=None):
         if compute_device is not None:

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/core/vram/layers.py

@@ -128,6 +128,7 @@ class AutoWrappedModule(AutoTorchModule):
         else:
             self.disk_offload = False
             
+    @torch._dynamo.disable
     def load_from_disk(self, torch_dtype, device, copy_module=False):
         if copy_module:
             module = copy.deepcopy(self.module)
@@ -245,6 +246,7 @@ class AutoWrappedNonRecurseModule(AutoWrappedModule):
         if self.disk_offload:
             self.required_params = [name for name, _ in self.module.named_parameters(recurse=False)]
             
+    @torch._dynamo.disable
     def load_from_disk(self, torch_dtype, device, copy_module=False):
         if copy_module:
             module = copy.deepcopy(self.module)
@@ -374,6 +376,7 @@ class AutoWrappedLinear(torch.nn.Linear, AutoTorchModule, LoRAHotLoadMixin):
         result = result.reshape(new_shape)
         return result
             
+    @torch._dynamo.disable
     def load_from_disk(self, torch_dtype, device, assign=True):
         weight = self.disk_map[self.name + ".weight"].to(dtype=torch_dtype, device=device)
         bias = None if self.bias is None else self.disk_map[self.name + ".bias"].to(dtype=torch_dtype, device=device)
@@ -495,6 +498,7 @@ class AutoWrappedQuantizedModule(torch.nn.Linear, AutoTorchModule, LoRAHotLoadMi
             self._required_keys = [key for key in self.disk_map if key.startswith(self.name + ".")]
         return self._required_keys
 
+    @torch._dynamo.disable
     def _load_from_disk(self, device, target=None):
         module = self.module if target is None else target
         prefix = self.name + "."

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/diffusion/flow_match.py

@@ -5,16 +5,18 @@ from typing_extensions import Literal
 
 class FlowMatchScheduler():
 
-    def __init__(self, template: Literal["FLUX.1", "Wan", "Qwen-Image", "FLUX.2", "Z-Image", "LTX-2", "Qwen-Image-Lightning", "ERNIE-Image", "ACE-Step", "Ideogram4", "Krea-2", "Boogu", "MiniMax-H3", "MiniMax-Music3", "LingBot-Video", "SenseNova-U1", "YuE2"] = "FLUX.1"):
+    def __init__(self, template: Literal["FLUX.1", "Wan", "Qwen-Image", "FLUX.2", "FLUX.3", "Z-Image", "LTX-2", "Qwen-Image-Lightning", "ERNIE-Image", "MOSS-Image", "ACE-Step", "Ideogram4", "Krea-2", "Boogu", "MiniMax-H3", "MiniMax-Music3", "LingBot-Video", "SenseNova-U1", "YuE2"] = "FLUX.1"):
         self.set_timesteps_fn = {
             "FLUX.1": FlowMatchScheduler.set_timesteps_flux,
             "Wan": FlowMatchScheduler.set_timesteps_wan,
             "Qwen-Image": FlowMatchScheduler.set_timesteps_qwen_image,
             "FLUX.2": FlowMatchScheduler.set_timesteps_flux2,
+            "FLUX.3": FlowMatchScheduler.set_timesteps_flux3,
             "Z-Image": FlowMatchScheduler.set_timesteps_z_image,
             "LTX-2": FlowMatchScheduler.set_timesteps_ltx2,
             "Qwen-Image-Lightning": FlowMatchScheduler.set_timesteps_qwen_image_lightning,
             "ERNIE-Image": FlowMatchScheduler.set_timesteps_ernie_image,
+            "MOSS-Image": FlowMatchScheduler.set_timesteps_moss_image,
             "ACE-Step": FlowMatchScheduler.set_timesteps_ace_step,
             "HiDream-O1-Image": FlowMatchScheduler.set_timesteps_hidream_o1_image,
             "Ideogram4": FlowMatchScheduler.set_timesteps_ideogram4,
@@ -166,6 +168,13 @@ class FlowMatchScheduler():
         timesteps = sigmas * num_train_timesteps
         return sigmas, timesteps
 
+    @staticmethod
+    def set_timesteps_flux3(num_inference_steps=16, denoising_strength=1.0, alpha=6.93, **kwargs):
+        u = torch.linspace(denoising_strength, 0.0, num_inference_steps + 1)[:-1]
+        sigmas = alpha * u / (1.0 + (alpha - 1.0) * u)
+        timesteps = sigmas * 1000
+        return sigmas, timesteps
+
     @staticmethod
     def set_timesteps_ernie_image(num_inference_steps=50, denoising_strength=1.0, shift=3.0):
         sigma_min = 0.0
@@ -178,6 +187,25 @@ class FlowMatchScheduler():
         timesteps = sigmas * num_train_timesteps
         return sigmas, timesteps
 
+    @staticmethod
+    def set_timesteps_moss_image(num_inference_steps=50, denoising_strength=1.0, shift=5.0, training_shift=1.0):
+        num_train_timesteps = 1000
+
+        def grid(count, shift, start=1.0):
+            lower = shift / (num_train_timesteps + shift - 1)
+            values = torch.linspace(start, lower, count)
+            return shift * values / (1 + (shift - 1) * values)
+
+        sigmas = grid(num_inference_steps, shift, denoising_strength)
+        training = grid(num_train_timesteps, training_shift).flip(0)
+        upper = torch.searchsorted(training, sigmas).clamp(max=num_train_timesteps - 1)
+        lower = (upper - 1).clamp(min=0)
+        nearest = torch.where((sigmas - training[lower]).abs() <= (training[upper] - sigmas).abs(), lower, upper)
+
+        sigmas = torch.unique_consecutive(training[nearest])
+        timesteps = sigmas * num_train_timesteps
+        return sigmas, timesteps
+
     @staticmethod
     def set_timesteps_sensenova_u1(num_inference_steps=50, denoising_strength=1.0, shift=3.0):
         num_train_timesteps = 1000

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/diffusion/parsers.py

@@ -32,7 +32,7 @@ def add_model_config(parser: argparse.ArgumentParser):
     return parser
 
 def add_quant_config(parser: argparse.ArgumentParser):
-    parser.add_argument("--quant_options", type=str, default=None, help="Dynamically quantize loaded models. Semicolon-separated entries, each `<model_string>:<method>[/<exclude_modules>]`, where `<model_string>` matches an entry in `--model_paths`/`--model_id_with_origin_paths`, `method` is a registered method (e.g. bitsandbytes_nf4), and `exclude_modules` optionally lists layers kept in full precision.")
+    parser.add_argument("--quant_options", type=str, default=None, help="Dynamically quantize loaded models. Semicolon-separated entries, each `<model_string>:<method>[/<exclude_modules>]`, where `<model_string>` matches an entry in `--model_paths`/`--model_id_with_origin_paths`, `method` is a registered method (e.g. bitsandbytes_nf4), and `exclude_modules` optionally lists layers kept in full precision. Alternatively, pass a JSON object mapping the same model strings to configs: `method`, optional `backend_config_kwargs` (method-specific parameters), and `target_modules`/`exclude_modules` (JSON lists of layer names). For example: --quant_options '{\"org/model:transformer/*.safetensors\": {\"method\": \"bitsandbytes_nf4\", \"backend_config_kwargs\": {\"blocksize\": 64}, \"exclude_modules\": [\"to_q\"]}}'. For mixed quantization, use a `configs` list of these configs instead of `method`, with `target_modules`/`exclude_modules` selecting non-overlapping layer sets.")
     return parser
 
 def add_training_config(parser: argparse.ArgumentParser):

{diffsynth-2.1.9 → diffsynth-2.1.10}/diffsynth/diffusion/training_module.py

@@ -1,5 +1,6 @@
 import torch, json, os, inspect
 from ..core import ModelConfig, load_state_dict, QuantizeConfig
+from ..core.quant import MixedQuantizeConfig
 from ..utils.controlnet import ControlNetInput
 from .base_pipeline import PipelineUnit
 
@@ -180,6 +181,26 @@ class DiffusionTrainingModule(torch.nn.Module):
         quant_map = {}
         if quant_options is None:
             return quant_map
+
+        # JSON format
+        if quant_options.lstrip().startswith("{"):
+            json_options = json.loads(quant_options)
+            for model_string, value in json_options.items():
+                if not isinstance(value, dict):
+                    raise ValueError(f"Failed to parse quant option JSON: the config for `{model_string}` must be an object, got {type(value).__name__}.")
+                child_configs = value.pop("configs", None)
+                for config_dict in [value] + (child_configs if isinstance(child_configs, list) else []):
+                    if isinstance(config_dict, dict) and not isinstance(config_dict.get("load_prequantized", False), bool):
+                        raise ValueError(f"Failed to parse quant option JSON: `load_prequantized` for `{model_string}` must be a boolean, got {type(config_dict['load_prequantized']).__name__}.")
+                configs = [QuantizeConfig(**child) for child in (child_configs if child_configs is not None else [value])]
+                quant_config = configs[0] if child_configs is None else MixedQuantizeConfig(configs=configs, **value)
+                methods = [config.method for config in configs if not config.backend.capabilities().get("is_differentiable", True)]
+                if methods:
+                    raise ValueError(f"Quantization method(s) {methods} are not differentiable, so they cannot be used for training.")
+                quant_map[self.normalize_quant_key(model_string)] = quant_config
+            return quant_map
+
+        # Semicolon-separated format
         for entry in quant_options.split(";"):
             if entry == "":
                 continue