| 开源引入 |
https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/diffusion_utils_2.py |
mindspeed_mm/models/diffusion/ddpm.py |
https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/diffusion_utils_2.py |
开源代码参考链接 |
| 开源引入 |
https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py |
mindspeed_mm/models/diffusion/ddpm.py |
https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py |
开源代码参考链接 |
| 开源引入 |
https://github.com/PKU-YuanGroup/Open-Sora-Plan/blob/main/opensora/sample/pipeline_opensora.py |
mindspeed_mm/models/diffusion/diffusers_scheduler.py |
https://arxiv.org/pdf/2205.11487.pdf |
Imagen论文链接 |
| 开源引入 |
https://github.com/openai/guided-diffusion/blob/main/guided_diffusion |
mindspeed_mm/models/diffusion/diffusion_utils.py |
https://github.com/openai/guided-diffusion/blob/main/guided_diffusion |
开源代码参考链接 |
| 开源引入 |
https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py |
mindspeed_mm/models/diffusion/diffusion_utils.py |
https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py |
开源代码参考链接 |
| 开源引入 |
https://github.com/PKU-YuanGroup/Open-Sora-Plan/tree/v1.1.0/opensora/models/diffusion/diffusion |
mindspeed_mm/models/diffusion/iddpm.py |
https://github.com/PKU-YuanGroup/Open-Sora-Plan/tree/v1.1.0/opensora/models/diffusion/diffusion |
开源代码参考链接 |
| 开源引入 |
https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py |
mindspeed_mm/models/diffusion/iddpm.py |
https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py |
开源代码参考链接 |
| 开发引入 |
/ |
./mindspeed_mm/models/common/embeddings/__init__.py |
https://github.com/PKU-YuanGroup/Open-Sora-Plan |
开源代码参考指引 |
| 开发引入 |
/ |
./mindspeed_mm/models/common/embeddings/__init__.py |
https://github.com/facebookresearch/DiT/tree/main |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/models/common/embeddings/__init__.py |
https://github.com/PixArt-alpha/PixArt-alpha |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/models/common/embeddings/__init__.py |
https://github.com/hpcaitech/Open-Sora/ |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/data/data_utils/data_transform.py |
https://github.com/Vchitect/Latte/blob/main/datasets/video_transforms.py |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/data/data_utils/utils.py |
https://github.com/dmlc/decord |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/data/data_utils/utils.py |
https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/data/dataloader/dataloader.py |
https://github.com/hpcaitech/Open-Sora/tree/main/opensora/datasets |
开源代码参考指引 |
| 开发引入 |
/ |
.mindspeed_mm/data/dataloader/sampler.py |
https://github.com/hpcaitech/Open-Sora/tree/main/opensora/datasets |
开源代码参考指引 |
| 开源引入 |
https://raw.githubusercontent.com/huggingface/diffusers/main/examples/text_to_image/train_text_to_image_sdxl.py |
./train_text_to_image_sdxl.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开源引入 |
https://raw.githubusercontent.com/huggingface/diffusers/main/examples/dreambooth/train_dreambooth_sd3.py |
./train_dreambooth_sd3.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开发引入 |
https://github.com/PKU-YuanGroup/Open-Sora-Plan/blob/main/opensora/sample/pipeline_opensora.py |
mindspeed_mm/tasks/inference/pipeline/opensoraplan_pipeline.py |
https://arxiv.org/abs/2010.02502 |
开源代码参考指引 |
| 开发引入 |
/ |
mindspeed_mm/models/diffusion/diffusers_scheduler.py |
https://arxiv.org/pdf/2205.11487.pdf |
参考论文地址 |
| 开发引入 |
/ |
mindspeed_mm/models/diffusion/diffusers_scheduler.py |
https://arxiv.org/abs/2303.09556 |
参考论文地址 |
| 开发引入 |
/ |
mindspeed_mm/models/diffusion/diffusers_scheduler.py |
https://www.crosslabs.org//blog/diffusion-with-offset-noise |
参考博客地址 |
| 开源引入 |
https://github.com/microsoft/DeepSpeed/blob/master/tests/conftest.py |
./tests/conftest.py |
https://github.com/microsoft/DeepSpeed/blob/master/tests/conftest.py |
开源代码参考链接 |
| 开源引入 |
Python三方件diffusers的CogVideoXPipeline模块 |
mindspeed_mm/tasks/inference/pipeline/cogvideox_pipeline.py |
http://www.apache.org/licenses/LICENSE-2.0 |
参考开源三方件文件头声明 |
| 开源引入 |
Python三方件diffusers的CogVideoXPipeline模块 |
mindspeed_mm/tasks/inference/pipeline/cogvideox_pipeline.py |
http://arxiv.org/abs/2010.02502 |
开源代码参考指引 |
| 开源引入 |
https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_flux.py |
./train_dreambooth_flux.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开源引入 |
https://github.com/hiyouga/LLaMA-Factory/blob/main/src/llamafactory/hparams/model_args.py |
mindspeed_mm/data/data_utils/func_utils/model_args.py |
https://github.com/huggingface/transformers/blob/v4.40.0/examples/pytorch/language-modeling/run_clm.py |
开源代码参考指引 |
| 开源引入 |
https://github.com/hiyouga/LLaMA-Factory/blob/main/src/llamafactory/model/loader.py |
mindspeed_mm/data/data_utils/func_utils/convert.py |
https://github.com/huggingface/transformers/blob/v4.40.0/src/transformers/models/auto/processing_auto.py#L324 |
开源代码参考指引 |
| 开源引入 |
https://github.com/hiyouga/LLaMA-Factory/blob/main/src/llamafactory/data/collator.py |
mindspeed_mm/data/data_utils/func_utils/collator.py |
https://github.com/OpenAccess-AI-Collective/axolotl/blob/main/src/axolotl/monkeypatch/utils.py |
开源代码参考指引 |
| 开源引入 |
https://github.com/open-compass/VLMEvalKit/blob/main/vlmeval/dataset/utils/vqa_eval.py |
mindspeed_mm/tasks/evaluation/utils/string_utils.py |
https://github.com/GT-Vision-Lab/VQA |
开源代码参考指引 |
| 开源引入 |
https://github.com/OpenGVLab/InternVL/blob/main/internvl_chat/internvl/conversation.py |
mindspeed_mm/data/data_utils/conversation.py |
https://github.com/OpenGVLab/InternVL |
开源代码参考指引 |
| 开源引入 |
https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sana.py |
MindSpeed-MM/sana/MindSpeed-MM/examples/diffusers/sana/patch_sana.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开源引入 |
https://github.com/huggingface/diffusers/pull/6514#discussion_r1449796804 |
MindSpeed-MM/sana/MindSpeed-MM/examples/diffusers/sana/patch_sana.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开发引入 |
/ |
./mindspeed_mm/models/predictor/dits/pt_dit_diffusers.py |
https://github.com/PixArt-alpha/PixArt-alpha/blob/0f55e922376d8b797edd44d25d0e7464b260dcab/diffusion/model/nets/PixArtMS.py#L164C9-L168C29 |
开源代码参考指引 |
| 开发引入 |
/ |
./mindspeed_mm/models/predictor/dits/pt_dit_diffusers.py |
https://arxiv.org/abs/2310.00426 |
参考论文地址 |
| 开发引入 |
/ |
./mindspeed_mm/models/predictor/dits/pt_dit_diffusers.py |
https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py |
开源代码参考指引 |
| 开源引入 |
https://github.com/deepseek-ai/DeepSeek-VL2/blob/main/deepseek_vl2/models/modeling_deepseek_vl_v2.py |
mindspeed_mm/models/vision/vision_encoders/siglip_vit_model.py |
https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py |
开源代码参考指引 |
| 开源引入 |
https://github.com/deepseek-ai/DeepSeek-VL2/blob/main/deepseek_vl2/models/modeling_deepseek_vl_v2.py |
mindspeed_mm/models/vision/vision_encoders/siglip_vit_model.py |
https://people.sc.fsu.edu/~jburkardt/presentations/truncated_normal.pdf |
开源代码参考指引 |
| 开源引入 |
https://github.com/deepseek-ai/DeepSeek-VL2/blob/main/deepseek_vl2/models/modeling_deepseek_vl_v2.py |
mindspeed_mm/models/vision/vision_encoders/siglip_vit_model.py |
https://arxiv.org/abs/2010.11929 |
开源代码参考指引 |
| 开源引入 |
https://github.com/deepseek-ai/DeepSeek-VL2/blob/main/deepseek_vl2/models/modeling_deepseek_vl_v2.py |
mindspeed_mm/models/vision/vision_encoders/siglip_vit_model.py |
https://github.com/huggingface/transformers/blob/78b2929c0554b79e0489b451ce4ece14d265ead2/src/transformers/models/siglip/configuration_siglip.py#L191 |
开源代码参考指引 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/dataset/latent_flux_rl_datasets.py |
mindspeed_mm/tasks/rl/soragrpo/dataset/latent_flux_rl_datasets.py |
https://github.com/hao-ai-lab/FastVideo/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/data_preprocess/preprocess_flux_embedding.py |
mindspeed_mm/tasks/rl/soragrpo/preprocess/data_preprocess.py |
https://github.com/hao-ai-lab/FastVideo/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/data_preprocess/preprocess_flux_embedding.py |
mindspeed_mm/tasks/rl/soragrpo/preprocess/flux_data_preprocess.py |
https://github.com/hao-ai-lab/FastVideo/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/utils/communications_flux.py |
mindspeed_mm/tasks/rl/soragrpo/utils/communications_flux.py |
https://github.com/hao-ai-lab/FastVideo/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/utils/fsdp_util.py |
mindspeed_mm/tasks/rl/soragrpo/utils/fsdp_util.py |
https://github.com/hao-ai-lab/FastVideo |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/utils/parallel_states.py |
mindspeed_mm/tasks/rl/soragrpo/utils/parallel_states.py |
https://github.com/hao-ai-lab/FastVideo |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/train_grpo_flux.py |
mindspeed_mm/tasks/rl/soragrpo/flux_grpo_trainer.py |
https://github.com/hao-ai-lab/FastVideo/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/XueZeyue/DanceGRPO/blob/main/fastvideo/train_grpo_flux.py |
mindspeed_mm/tasks/rl/soragrpo/sora_grpo_trainer.py |
https://github.com/hao-ai-lab/FastVideo/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/hyvideo/models/transformers/hunyuanvideo_1_5_transformer.py |
mindspeed_mm/models/predictor/dits/hunyuan_video_15_dit.py |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/hyvideo/models/transformers/hunyuanvideo_1_5_transformer.py |
mindspeed_mm/models/predictor/dits/hunyuan_video_15_dit.py |
http://arxiv.org/abs/2406.11831 |
参考论文地址 |
| 开源引入 |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/hyvideo/models/text_encoders/byT5/__init__.py |
mindspeed_mm/models/text_encoder/byt5/init.py |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/hyvideo/models/text_encoders/byT5/format_prompt.py |
mindspeed_mm/models/text_encoder/byt5/format_prompt.py |
https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/LICENSE |
开源代码参考链接 |
| 开源引入 |
https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_hidream_image.py |
mindspeed_mm/examples/diffusers/hidream/transformer_patches.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开源引入 |
https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_flux.py |
mindspeed_mm/examples/diffusers/flux-kontext/transformer_patches.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开源引入 |
https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_flux2.py |
mindspeed_mm/examples/diffusers/flux2/transformer_patches.py |
https://github.com/huggingface/diffusers |
开源代码参考指引 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu124 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu121 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu120 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu118 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu117 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu116 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu102 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cu121 |
开源软件安装地址 |
| 开发引入 |
/ |
scripts/install.sh |
https://download.pytorch.org/whl/cpu |
开源软件安装地址 |
