diffsynth 2.1.0__tar.gz → 2.1.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (260) hide show
  1. {diffsynth-2.1.0 → diffsynth-2.1.1}/PKG-INFO +1 -1
  2. {diffsynth-2.1.0 → diffsynth-2.1.1}/README.md +40 -35
  3. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/configs/model_configs.py +7 -0
  4. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/configs/vram_management_module_maps.py +9 -0
  5. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/attention/attention.py +41 -3
  6. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/vram/layers.py +3 -2
  7. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/flow_match.py +1 -1
  8. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/loss.py +12 -11
  9. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/minimax_h3_dit.py +4 -3
  10. diffsynth-2.1.1/diffsynth/models/wan_animate_2_dit.py +913 -0
  11. diffsynth-2.1.1/diffsynth/pipelines/minimax_h3_audio_video.py +884 -0
  12. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/wan_video.py +263 -8
  13. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/data/audio_video.py +83 -7
  14. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/xfuser/__init__.py +1 -1
  15. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/xfuser/xdit_context_parallel.py +13 -0
  16. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth.egg-info/PKG-INFO +1 -1
  17. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth.egg-info/SOURCES.txt +1 -1
  18. {diffsynth-2.1.0 → diffsynth-2.1.1}/pyproject.toml +1 -1
  19. diffsynth-2.1.0/diffsynth/models/minimax_constant.py +0 -23
  20. diffsynth-2.1.0/diffsynth/pipelines/minimax_h3_audio_video.py +0 -1062
  21. {diffsynth-2.1.0 → diffsynth-2.1.1}/LICENSE +0 -0
  22. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/__init__.py +0 -0
  23. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/configs/__init__.py +0 -0
  24. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/__init__.py +0 -0
  25. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/attention/__init__.py +0 -0
  26. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/data/__init__.py +0 -0
  27. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/data/operators.py +0 -0
  28. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/data/unified_dataset.py +0 -0
  29. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/device/__init__.py +0 -0
  30. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/device/npu_compatible_device.py +0 -0
  31. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/gradient/__init__.py +0 -0
  32. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/gradient/gradient_checkpoint.py +0 -0
  33. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/loader/__init__.py +0 -0
  34. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/loader/config.py +0 -0
  35. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/loader/file.py +0 -0
  36. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/loader/model.py +0 -0
  37. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/npu_patch/npu_fused_operator.py +0 -0
  38. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/offload_training/__init__.py +0 -0
  39. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/offload_training/manager.py +0 -0
  40. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/offload_training/memory_buffer.py +0 -0
  41. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/offload_training/offloader.py +0 -0
  42. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/quant/__init__.py +0 -0
  43. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/quant/backends/__init__.py +0 -0
  44. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/quant/backends/bitsandbytes.py +0 -0
  45. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/quant/backends/torchao.py +0 -0
  46. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/quant/base.py +0 -0
  47. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/quant/config.py +0 -0
  48. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/vram/__init__.py +0 -0
  49. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/vram/disk_map.py +0 -0
  50. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/core/vram/initialization.py +0 -0
  51. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/__init__.py +0 -0
  52. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/base_pipeline.py +0 -0
  53. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/ddim_scheduler.py +0 -0
  54. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/dmd2.py +0 -0
  55. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/logger.py +0 -0
  56. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/parsers.py +0 -0
  57. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/runner.py +0 -0
  58. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/template.py +0 -0
  59. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/diffusion/training_module.py +0 -0
  60. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/__init__.py +0 -0
  61. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/aesthetic.py +0 -0
  62. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/base.py +0 -0
  63. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/bioclip.py +0 -0
  64. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/clip.py +0 -0
  65. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/fid.py +0 -0
  66. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/hpsv2.py +0 -0
  67. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/hpsv3.py +0 -0
  68. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/image_reward.py +0 -0
  69. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/lpips.py +0 -0
  70. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/pickscore.py +0 -0
  71. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/qwen_image_bench.py +0 -0
  72. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/unified_reward_2.py +0 -0
  73. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/metrics/unified_reward_edit.py +0 -0
  74. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ace_step_conditioner.py +0 -0
  75. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ace_step_dit.py +0 -0
  76. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ace_step_residual_fsq.py +0 -0
  77. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ace_step_text_encoder.py +0 -0
  78. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ace_step_tokenizer.py +0 -0
  79. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ace_step_vae.py +0 -0
  80. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/aesthetic.py +0 -0
  81. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/anima_dit.py +0 -0
  82. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/bioclip.py +0 -0
  83. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/boogu_image_dit.py +0 -0
  84. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/clip.py +0 -0
  85. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/demucs.py +0 -0
  86. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/dinov3_image_encoder.py +0 -0
  87. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ernie_image_dit.py +0 -0
  88. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ernie_image_text_encoder.py +0 -0
  89. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/fid.py +0 -0
  90. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux2_dit.py +0 -0
  91. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux2_text_encoder.py +0 -0
  92. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux2_vae.py +0 -0
  93. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_controlnet.py +0 -0
  94. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_dit.py +0 -0
  95. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_infiniteyou.py +0 -0
  96. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_ipadapter.py +0 -0
  97. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_lora_encoder.py +0 -0
  98. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_lora_patcher.py +0 -0
  99. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_text_encoder_clip.py +0 -0
  100. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_text_encoder_t5.py +0 -0
  101. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_vae.py +0 -0
  102. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/flux_value_control.py +0 -0
  103. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/general_modules.py +0 -0
  104. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/hidream_common.py +0 -0
  105. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/hidream_o1_image_dit.py +0 -0
  106. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/hpsv2.py +0 -0
  107. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/hpsv3.py +0 -0
  108. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ideogram4_dit.py +0 -0
  109. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ideogram4_text_encoder.py +0 -0
  110. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ideogram4_vae.py +0 -0
  111. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/image_reward.py +0 -0
  112. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/joyai_image_dit.py +0 -0
  113. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/joyai_image_text_encoder.py +0 -0
  114. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/krea2_dit.py +0 -0
  115. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/krea2_text_encoder.py +0 -0
  116. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/lingbot_video_dit.py +0 -0
  117. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/longcat_video_dit.py +0 -0
  118. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/lpips.py +0 -0
  119. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ltx2_audio_vae.py +0 -0
  120. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ltx2_common.py +0 -0
  121. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ltx2_dit.py +0 -0
  122. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ltx2_text_encoder.py +0 -0
  123. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ltx2_upsampler.py +0 -0
  124. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/ltx2_video_vae.py +0 -0
  125. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/minimax_h3_audio_vae.py +0 -0
  126. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/minimax_h3_text_encoder.py +0 -0
  127. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/minimax_h3_video_vae.py +0 -0
  128. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/model_loader.py +0 -0
  129. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/mova_audio_dit.py +0 -0
  130. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/mova_audio_vae.py +0 -0
  131. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/mova_dual_tower_bridge.py +0 -0
  132. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/nexus_gen.py +0 -0
  133. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/nexus_gen_ar_model.py +0 -0
  134. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/nexus_gen_projector.py +0 -0
  135. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/pickscore.py +0 -0
  136. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/qwen_image_bench.py +0 -0
  137. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/qwen_image_controlnet.py +0 -0
  138. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/qwen_image_dit.py +0 -0
  139. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/qwen_image_image2lora.py +0 -0
  140. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/qwen_image_text_encoder.py +0 -0
  141. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/qwen_image_vae.py +0 -0
  142. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/sd_text_encoder.py +0 -0
  143. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/siglip2_image_encoder.py +0 -0
  144. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/stable_diffusion_text_encoder.py +0 -0
  145. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/stable_diffusion_unet.py +0 -0
  146. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/stable_diffusion_vae.py +0 -0
  147. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/stable_diffusion_xl_text_encoder.py +0 -0
  148. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/stable_diffusion_xl_unet.py +0 -0
  149. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/step1x_connector.py +0 -0
  150. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/step1x_text_encoder.py +0 -0
  151. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/unified_reward_2.py +0 -0
  152. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/unified_reward_edit.py +0 -0
  153. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_animate_adapter.py +0 -0
  154. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_camera_controller.py +0 -0
  155. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_dit.py +0 -0
  156. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_dit_s2v.py +0 -0
  157. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_image_encoder.py +0 -0
  158. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_mot.py +0 -0
  159. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_motion_controller.py +0 -0
  160. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_text_encoder.py +0 -0
  161. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_vace.py +0 -0
  162. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wan_video_vae.py +0 -0
  163. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wantodance.py +0 -0
  164. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/wav2vec.py +0 -0
  165. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/z_image_controlnet.py +0 -0
  166. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/z_image_dit.py +0 -0
  167. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/z_image_image2lora.py +0 -0
  168. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/models/z_image_text_encoder.py +0 -0
  169. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/ace_step.py +0 -0
  170. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/anima_image.py +0 -0
  171. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/boogu_image.py +0 -0
  172. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/ernie_image.py +0 -0
  173. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/flux2_image.py +0 -0
  174. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/flux_image.py +0 -0
  175. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/hidream_o1_image.py +0 -0
  176. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/ideogram4.py +0 -0
  177. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/joyai_image.py +0 -0
  178. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/krea2.py +0 -0
  179. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/lingbot_video.py +0 -0
  180. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/ltx2_audio_video.py +0 -0
  181. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/mova_audio_video.py +0 -0
  182. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/qwen_image.py +0 -0
  183. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/stable_diffusion.py +0 -0
  184. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/stable_diffusion_xl.py +0 -0
  185. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/pipelines/z_image.py +0 -0
  186. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/controlnet/__init__.py +0 -0
  187. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/controlnet/annotator.py +0 -0
  188. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/controlnet/controlnet_input.py +0 -0
  189. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/data/__init__.py +0 -0
  190. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/data/audio.py +0 -0
  191. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/data/media_io_ltx2.py +0 -0
  192. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/data/minimax_h3.py +0 -0
  193. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/demucs/__init__.py +0 -0
  194. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/dequantizer/__init__.py +0 -0
  195. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/__init__.py +0 -0
  196. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/flux.py +0 -0
  197. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/flux_timestep.py +0 -0
  198. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/general.py +0 -0
  199. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/krea2.py +0 -0
  200. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/merge.py +0 -0
  201. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/reset_rank.py +0 -0
  202. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/lora/sdxl.py +0 -0
  203. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/ses/__init__.py +0 -0
  204. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/ses/ses.py +0 -0
  205. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/__init__.py +0 -0
  206. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ace_step_conditioner.py +0 -0
  207. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ace_step_dit.py +0 -0
  208. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ace_step_text_encoder.py +0 -0
  209. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ace_step_tokenizer.py +0 -0
  210. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/anima_dit.py +0 -0
  211. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/dino_v3.py +0 -0
  212. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ernie_image_text_encoder.py +0 -0
  213. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux2_text_encoder.py +0 -0
  214. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_controlnet.py +0 -0
  215. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_dit.py +0 -0
  216. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_infiniteyou.py +0 -0
  217. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_ipadapter.py +0 -0
  218. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_text_encoder_clip.py +0 -0
  219. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_text_encoder_t5.py +0 -0
  220. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/flux_vae.py +0 -0
  221. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ideogram4_text_encoder.py +0 -0
  222. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/image_metrics.py +0 -0
  223. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/joyai_image_text_encoder.py +0 -0
  224. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/krea2_dit.py +0 -0
  225. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/krea2_text_encoder.py +0 -0
  226. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/lingbot_video_dit.py +0 -0
  227. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ltx2_audio_vae.py +0 -0
  228. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ltx2_dit.py +0 -0
  229. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ltx2_text_encoder.py +0 -0
  230. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/ltx2_video_vae.py +0 -0
  231. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/minimax_h3_audio_vae.py +0 -0
  232. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/minimax_h3_text_encoder.py +0 -0
  233. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/minimax_h3_video_vae.py +0 -0
  234. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/nexus_gen.py +0 -0
  235. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/nexus_gen_projector.py +0 -0
  236. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/qwen_image_text_encoder.py +0 -0
  237. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/sdxl.py +0 -0
  238. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/sdxl_text_encoder.py +0 -0
  239. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/sdxl_text_encoder_2.py +0 -0
  240. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/sdxl_vae.py +0 -0
  241. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/stable_diffusion_text_encoder.py +0 -0
  242. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/stable_diffusion_vae.py +0 -0
  243. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/stable_diffusion_xl_text_encoder.py +0 -0
  244. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/step1x_connector.py +0 -0
  245. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wan_video_animate_adapter.py +0 -0
  246. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wan_video_dit.py +0 -0
  247. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wan_video_image_encoder.py +0 -0
  248. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wan_video_mot.py +0 -0
  249. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wan_video_vace.py +0 -0
  250. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wan_video_vae.py +0 -0
  251. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/wans2v_audio_encoder.py +0 -0
  252. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/z_image_dit.py +0 -0
  253. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/state_dict_converters/z_image_text_encoder.py +0 -0
  254. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/tile/__init__.py +0 -0
  255. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/utils/tile/tile_worker.py +0 -0
  256. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth/version.py +0 -0
  257. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth.egg-info/dependency_links.txt +0 -0
  258. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth.egg-info/requires.txt +0 -0
  259. {diffsynth-2.1.0 → diffsynth-2.1.1}/diffsynth.egg-info/top_level.txt +0 -0
  260. {diffsynth-2.1.0 → diffsynth-2.1.1}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: diffsynth
3
- Version: 2.1.0
3
+ Version: 2.1.1
4
4
  Summary: Enjoy the magic of Diffusion models!
5
5
  Author: ModelScope Team
6
6
  License: Apache-2.0
@@ -36,6 +36,8 @@ We believe that a well-developed open-source code framework can lower the thresh
36
36
 
37
37
  > 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.
38
38
 
39
+ - **August 7, 2026** We add support for Wan-Animate-2 in the Wan series. Given a reference image and a driving video, it makes the reference character perform the motions in the driving video, generating high-quality character animation, with both standard and distilled variants. For details, please refer to the [documentation](/docs/en/Model_Details/Wan.md) and [example code](/examples/wanvideo/).
40
+
39
41
  - **August 3, 2026** MiniMax-H3 open-sourced, welcome a new member to the video model family! Support includes text-to-video-audio generation, keyframe-guided generation, reference-driven generation, low VRAM inference, and NF4-quantized inference. For details, please refer to the [documentation](/docs/en/Model_Details/MiniMax-H3.md) and [example code](/examples/minimax_h3/).
40
42
 
41
43
  - **July 28, 2026** LingBot-Video open-sourced, welcome a new member to the video model family! This release includes two variants, Dense-1.3B and MoE-30B-A3B (30B total parameters, ~3B active per token), both supporting text-to-video, image-to-video and text-to-image generation, low VRAM inference, and LoRA / full training capabilities. For details, please refer to the [documentation](/docs/en/Model_Details/LingBot-Video.md) and [example code](/examples/lingbot_video/). Huge thanks to [NancyFyong](https://github.com/NancyFyong) for contributing the integration of this model!
@@ -1413,41 +1415,43 @@ Example code for Wan is available at: [/examples/wanvideo/](/examples/wanvideo/)
1413
1415
 
1414
1416
  | Model ID | Extra Inputs | Inference | Low VRAM Inference | Full Training | Validation After Full Training | LoRA Training | Validation After LoRA Training |
1415
1417
  |-|-|-|-|-|-|-|-|
1416
- |[Wan-AI/Wan2.1-T2V-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-T2V-1.3B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-T2V-1.3B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-T2V-1.3B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-T2V-1.3B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-T2V-1.3B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-1.3B.py)|
1417
- |[Wan-AI/Wan2.1-T2V-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-T2V-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-T2V-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-T2V-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-T2V-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-T2V-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-14B.py)|
1418
- |[Wan-AI/Wan2.1-I2V-14B-480P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)|`input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-I2V-14B-480P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-I2V-14B-480P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-I2V-14B-480P.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-I2V-14B-480P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-I2V-14B-480P.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-I2V-14B-480P.py)|
1419
- |[Wan-AI/Wan2.1-I2V-14B-720P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-720P)|`input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-I2V-14B-720P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-I2V-14B-720P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-I2V-14B-720P.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-I2V-14B-720P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-I2V-14B-720P.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-I2V-14B-720P.py)|
1420
- |[Wan-AI/Wan2.1-FLF2V-14B-720P](https://modelscope.cn/models/Wan-AI/Wan2.1-FLF2V-14B-720P)|`input_image`, `end_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-FLF2V-14B-720P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-FLF2V-14B-720P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-FLF2V-14B-720P.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-FLF2V-14B-720P.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-FLF2V-14B-720P.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-FLF2V-14B-720P.py)|
1421
- |[iic/VACE-Wan2.1-1.3B-Preview](https://modelscope.cn/models/iic/VACE-Wan2.1-1.3B-Preview)|`vace_control_video`, `vace_reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B-Preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-VACE-1.3B-Preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-1.3B-Preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-VACE-1.3B-Preview.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-VACE-1.3B-Preview.py)|
1422
- |[Wan-AI/Wan2.1-VACE-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-VACE-1.3B)|`vace_control_video`, `vace_reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-VACE-1.3B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-1.3B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-VACE-1.3B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-VACE-1.3B.py)|
1423
- |[Wan-AI/Wan2.1-VACE-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-VACE-14B)|`vace_control_video`, `vace_reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-VACE-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-VACE-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-VACE-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-VACE-14B.py)|
1424
- |[PAI/Wan2.1-Fun-1.3B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-1.3B-InP)|`input_image`, `end_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-1.3B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-1.3B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-1.3B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-1.3B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-1.3B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-1.3B-InP.py)|
1425
- |[PAI/Wan2.1-Fun-1.3B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-1.3B-Control)|`control_video`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-1.3B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-1.3B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-1.3B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-1.3B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-1.3B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-1.3B-Control.py)|
1426
- |[PAI/Wan2.1-Fun-14B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-14B-InP)|`input_image`, `end_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-14B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-14B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-14B-InP.py)|
1427
- |[PAI/Wan2.1-Fun-14B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-14B-Control)|`control_video`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-14B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-14B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-14B-Control.py)|
1428
- |[PAI/Wan2.1-Fun-V1.1-1.3B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-Control)|`control_video`, `reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-Control.py)|
1429
- |[PAI/Wan2.1-Fun-V1.1-14B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-Control)|`control_video`, `reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-Control.py)|
1430
- |[PAI/Wan2.1-Fun-V1.1-1.3B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-InP)|`input_image`, `end_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-InP.py)|
1431
- |[PAI/Wan2.1-Fun-V1.1-14B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-InP)|`input_image`, `end_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-InP.py)|
1432
- |[PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera)|`control_camera_video`, `input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-Control-Camera.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-Control-Camera.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|
1433
- |[PAI/Wan2.1-Fun-V1.1-14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-Control-Camera)|`control_camera_video`, `input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-Control-Camera.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-Control-Camera.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|
1434
- |[DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1](https://modelscope.cn/models/DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1)|`motion_bucket_id`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.1-1.3b-speedcontrol-v1.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.1-1.3b-speedcontrol-v1.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.1-1.3b-speedcontrol-v1.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.1-1.3b-speedcontrol-v1.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.1-1.3b-speedcontrol-v1.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.1-1.3b-speedcontrol-v1.py)|
1435
- |[krea/krea-realtime-video](https://www.modelscope.cn/models/krea/krea-realtime-video)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/krea-realtime-video.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/krea-realtime-video.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/krea-realtime-video.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/krea-realtime-video.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/krea-realtime-video.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/krea-realtime-video.py)|
1436
- |[meituan-longcat/LongCat-Video](https://www.modelscope.cn/models/meituan-longcat/LongCat-Video)|`longcat_video`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/LongCat-Video.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/LongCat-Video.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/LongCat-Video.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/LongCat-Video.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/LongCat-Video.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/LongCat-Video.py)|
1437
- |[ByteDance/Video-As-Prompt-Wan2.1-14B](https://modelscope.cn/models/ByteDance/Video-As-Prompt-Wan2.1-14B)|`vap_video`, `vap_prompt`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Video-As-Prompt-Wan2.1-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Video-As-Prompt-Wan2.1-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Video-As-Prompt-Wan2.1-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Video-As-Prompt-Wan2.1-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Video-As-Prompt-Wan2.1-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Video-As-Prompt-Wan2.1-14B.py)|
1438
- |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-T2V-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-T2V-A14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-T2V-A14B.py)|
1439
- |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-I2V-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-I2V-A14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-I2V-A14B.py)|
1440
- |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-TI2V-5B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-TI2V-5B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-TI2V-5B.py)|
1441
- |[Wan-AI/Wan2.2-Animate-14B](https://www.modelscope.cn/models/Wan-AI/Wan2.2-Animate-14B)|`input_image`, `animate_pose_video`, `animate_face_video`, `animate_inpaint_video`, `animate_mask_video`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-Animate-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-Animate-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-Animate-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-Animate-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-Animate-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-Animate-14B.py)|
1442
- |[Wan-AI/Wan2.2-S2V-14B](https://www.modelscope.cn/models/Wan-AI/Wan2.2-S2V-14B)|`input_image`, `input_audio`, `audio_sample_rate`, `s2v_pose_video`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-S2V-14B_multi_clips.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-S2V-14B_multi_clips.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-S2V-14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-S2V-14B.py)|
1443
- |[PAI/Wan2.2-VACE-Fun-A14B](https://www.modelscope.cn/models/PAI/Wan2.2-VACE-Fun-A14B)|`vace_control_video`, `vace_reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-VACE-Fun-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-VACE-Fun-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-VACE-Fun-A14B.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-VACE-Fun-A14B.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py)|
1444
- |[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-Fun-A14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-Fun-A14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)|
1445
- |[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-Fun-A14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)|
1446
- |[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan2.2-Fun-A14B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)|
1447
- |[openmoss/MOVA-360p](https://modelscope.cn/models/openmoss/MOVA-360p)|`input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_inference/MOVA-360p-I2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_inference_low_vram/MOVA-360p-I2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/full/MOVA-360P-I2AV.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/validate_full/MOVA-360p-I2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/lora/MOVA-360P-I2AV.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/validate_lora/MOVA-360p-I2AV.py)|
1448
- |[openmoss/MOVA-720p](https://modelscope.cn/models/openmoss/MOVA-720p)|`input_image`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_inference/MOVA-720p-I2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_inference_low_vram/MOVA-720p-I2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/full/MOVA-720P-I2AV.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/validate_full/MOVA-720p-I2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/lora/MOVA-720P-I2AV.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/mova/model_training/validate_lora/MOVA-720p-I2AV.py)|
1449
- |[Wan-AI/Wan-Dancer-14B (global model)](https://modelscope.cn/models/Wan-AI/Wan-Dancer-14B)|`wantodance_music_path`, `wantodance_reference_image`, `wantodance_fps`, `wantodance_keyframes`, `wantodance_keyframes_mask`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan-Dancer-14B-global.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan-Dancer-14B-global.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan-Dancer-14B-global.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan-Dancer-14B-global.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan-Dancer-14B-global.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan-Dancer-14B-global.py)|
1450
- |[Wan-AI/Wan-Dancer-14B (local model)](https://modelscope.cn/models/Wan-AI/Wan-Dancer-14B)|`wantodance_music_path`, `wantodance_reference_image`, `wantodance_fps`, `wantodance_keyframes`, `wantodance_keyframes_mask`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference/Wan-Dancer-14B-local.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_inference_low_vram/Wan-Dancer-14B-local.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/full/Wan-Dancer-14B-local.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_full/Wan-Dancer-14B-local.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/lora/Wan-Dancer-14B-local.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/wanvideo/model_training/validate_lora/Wan-Dancer-14B-local.py)|
1418
+ |[Wan-AI/Wan2.1-T2V-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)||[code](/examples/wanvideo/model_inference/Wan2.1-T2V-1.3B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-T2V-1.3B.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-T2V-1.3B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-T2V-1.3B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-T2V-1.3B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-1.3B.py)|
1419
+ |[Wan-AI/Wan2.1-T2V-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)||[code](/examples/wanvideo/model_inference/Wan2.1-T2V-14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-T2V-14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-T2V-14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-T2V-14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-T2V-14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-14B.py)|
1420
+ |[Wan-AI/Wan2.1-I2V-14B-480P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)|`input_image`|[code](/examples/wanvideo/model_inference/Wan2.1-I2V-14B-480P.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-I2V-14B-480P.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-I2V-14B-480P.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-I2V-14B-480P.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-I2V-14B-480P.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-I2V-14B-480P.py)|
1421
+ |[Wan-AI/Wan2.1-I2V-14B-720P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-720P)|`input_image`|[code](/examples/wanvideo/model_inference/Wan2.1-I2V-14B-720P.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-I2V-14B-720P.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-I2V-14B-720P.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-I2V-14B-720P.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-I2V-14B-720P.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-I2V-14B-720P.py)|
1422
+ |[Wan-AI/Wan2.1-FLF2V-14B-720P](https://modelscope.cn/models/Wan-AI/Wan2.1-FLF2V-14B-720P)|`input_image`, `end_image`|[code](/examples/wanvideo/model_inference/Wan2.1-FLF2V-14B-720P.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-FLF2V-14B-720P.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-FLF2V-14B-720P.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-FLF2V-14B-720P.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-FLF2V-14B-720P.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-FLF2V-14B-720P.py)|
1423
+ |[iic/VACE-Wan2.1-1.3B-Preview](https://modelscope.cn/models/iic/VACE-Wan2.1-1.3B-Preview)|`vace_control_video`, `vace_reference_image`|[code](/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B-Preview.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-VACE-1.3B-Preview.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-1.3B-Preview.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-VACE-1.3B-Preview.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-VACE-1.3B-Preview.py)|
1424
+ |[Wan-AI/Wan2.1-VACE-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-VACE-1.3B)|`vace_control_video`, `vace_reference_image`|[code](/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-VACE-1.3B.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-1.3B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-VACE-1.3B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-VACE-1.3B.py)|
1425
+ |[Wan-AI/Wan2.1-VACE-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-VACE-14B)|`vace_control_video`, `vace_reference_image`|[code](/examples/wanvideo/model_inference/Wan2.1-VACE-14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-VACE-14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-VACE-14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-VACE-14B.py)|
1426
+ |[PAI/Wan2.1-Fun-1.3B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-1.3B-InP)|`input_image`, `end_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-1.3B-InP.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-1.3B-InP.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-1.3B-InP.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-1.3B-InP.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-1.3B-InP.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-1.3B-InP.py)|
1427
+ |[PAI/Wan2.1-Fun-1.3B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-1.3B-Control)|`control_video`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-1.3B-Control.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-1.3B-Control.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-1.3B-Control.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-1.3B-Control.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-1.3B-Control.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-1.3B-Control.py)|
1428
+ |[PAI/Wan2.1-Fun-14B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-14B-InP)|`input_image`, `end_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-14B-InP.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-14B-InP.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-14B-InP.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-14B-InP.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-14B-InP.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-14B-InP.py)|
1429
+ |[PAI/Wan2.1-Fun-14B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-14B-Control)|`control_video`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-14B-Control.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-14B-Control.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-14B-Control.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-14B-Control.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-14B-Control.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-14B-Control.py)|
1430
+ |[PAI/Wan2.1-Fun-V1.1-1.3B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-Control)|`control_video`, `reference_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-Control.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-Control.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-Control.py)|
1431
+ |[PAI/Wan2.1-Fun-V1.1-14B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-Control)|`control_video`, `reference_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-Control.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-14B-Control.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-Control.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-Control.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-Control.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-Control.py)|
1432
+ |[PAI/Wan2.1-Fun-V1.1-1.3B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-InP)|`input_image`, `end_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-InP.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-InP.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-InP.py)|
1433
+ |[PAI/Wan2.1-Fun-V1.1-14B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-InP)|`input_image`, `end_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-InP.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-14B-InP.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-InP.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-InP.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-InP.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-InP.py)|
1434
+ |[PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera)|`control_camera_video`, `input_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-Control-Camera.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-Control-Camera.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-Control-Camera.py)|
1435
+ |[PAI/Wan2.1-Fun-V1.1-14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-Control-Camera)|`control_camera_video`, `input_image`|[code](/examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-Control-Camera.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-Control-Camera.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-Control-Camera.py)|
1436
+ |[DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1](https://modelscope.cn/models/DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1)|`motion_bucket_id`|[code](/examples/wanvideo/model_inference/Wan2.1-1.3b-speedcontrol-v1.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.1-1.3b-speedcontrol-v1.py)|[code](/examples/wanvideo/model_training/full/Wan2.1-1.3b-speedcontrol-v1.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.1-1.3b-speedcontrol-v1.py)|[code](/examples/wanvideo/model_training/lora/Wan2.1-1.3b-speedcontrol-v1.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.1-1.3b-speedcontrol-v1.py)|
1437
+ |[krea/krea-realtime-video](https://www.modelscope.cn/models/krea/krea-realtime-video)||[code](/examples/wanvideo/model_inference/krea-realtime-video.py)|[code](/examples/wanvideo/model_inference_low_vram/krea-realtime-video.py)|[code](/examples/wanvideo/model_training/full/krea-realtime-video.sh)|[code](/examples/wanvideo/model_training/validate_full/krea-realtime-video.py)|[code](/examples/wanvideo/model_training/lora/krea-realtime-video.sh)|[code](/examples/wanvideo/model_training/validate_lora/krea-realtime-video.py)|
1438
+ |[meituan-longcat/LongCat-Video](https://www.modelscope.cn/models/meituan-longcat/LongCat-Video)|`longcat_video`|[code](/examples/wanvideo/model_inference/LongCat-Video.py)|[code](/examples/wanvideo/model_inference_low_vram/LongCat-Video.py)|[code](/examples/wanvideo/model_training/full/LongCat-Video.sh)|[code](/examples/wanvideo/model_training/validate_full/LongCat-Video.py)|[code](/examples/wanvideo/model_training/lora/LongCat-Video.sh)|[code](/examples/wanvideo/model_training/validate_lora/LongCat-Video.py)|
1439
+ |[ByteDance/Video-As-Prompt-Wan2.1-14B](https://modelscope.cn/models/ByteDance/Video-As-Prompt-Wan2.1-14B)|`vap_video`, `vap_prompt`|[code](/examples/wanvideo/model_inference/Video-As-Prompt-Wan2.1-14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Video-As-Prompt-Wan2.1-14B.py)|[code](/examples/wanvideo/model_training/full/Video-As-Prompt-Wan2.1-14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Video-As-Prompt-Wan2.1-14B.py)|[code](/examples/wanvideo/model_training/lora/Video-As-Prompt-Wan2.1-14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Video-As-Prompt-Wan2.1-14B.py)|
1440
+ |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](/examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-T2V-A14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-T2V-A14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-T2V-A14B.py)|
1441
+ |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](/examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-I2V-A14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-I2V-A14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-I2V-A14B.py)|
1442
+ |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](/examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-TI2V-5B.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-TI2V-5B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-TI2V-5B.py)|
1443
+ |[Wan-AI/Wan2.2-Animate-14B](https://www.modelscope.cn/models/Wan-AI/Wan2.2-Animate-14B)|`input_image`, `animate_pose_video`, `animate_face_video`, `animate_inpaint_video`, `animate_mask_video`|[code](/examples/wanvideo/model_inference/Wan2.2-Animate-14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-Animate-14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-Animate-14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-Animate-14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-Animate-14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-Animate-14B.py)|
1444
+ |[Wan-AI/Wan2.2-Animate-2-14B](https://www.modelscope.cn/models/Wan-AI/Wan2.2-Animate-2-14B)|`animate2_reference_image`, `animate2_reference_video`, `animate2_prompt_ref`|[code](/examples/wanvideo/model_inference/Wan2.2-Animate-2-14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-Animate-2-14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-Animate-2-14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-Animate-2-14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-Animate-2-14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-Animate-2-14B.py)|
1445
+ |[Wan-AI/Wan2.2-Animate-2-14B: Distilled](https://www.modelscope.cn/models/Wan-AI/Wan2.2-Animate-2-14B)|`animate2_reference_image`, `animate2_reference_video`, `animate2_prompt_ref`|[code](/examples/wanvideo/model_inference/Wan2.2-Animate-2-14B-Distilled.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-Animate-2-14B-Distilled.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-Animate-2-14B-Distilled.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-Animate-2-14B-Distilled.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-Animate-2-14B-Distilled.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-Animate-2-14B-Distilled.py)|
1446
+ |[Wan-AI/Wan2.2-S2V-14B](https://www.modelscope.cn/models/Wan-AI/Wan2.2-S2V-14B)|`input_image`, `input_audio`, `audio_sample_rate`, `s2v_pose_video`|[code](/examples/wanvideo/model_inference/Wan2.2-S2V-14B_multi_clips.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-S2V-14B_multi_clips.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-S2V-14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-S2V-14B.py)|
1447
+ |[PAI/Wan2.2-VACE-Fun-A14B](https://www.modelscope.cn/models/PAI/Wan2.2-VACE-Fun-A14B)|`vace_control_video`, `vace_reference_image`|[code](/examples/wanvideo/model_inference/Wan2.2-VACE-Fun-A14B.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-VACE-Fun-A14B.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-VACE-Fun-A14B.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-VACE-Fun-A14B.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py)|
1448
+ |[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](/examples/wanvideo/model_inference/Wan2.2-Fun-A14B-InP.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-Fun-A14B-InP.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)|
1449
+ |[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](/examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-Fun-A14B-Control.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)|
1450
+ |[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](/examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan2.2-Fun-A14B-Control-Camera.py)|[code](/examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](/examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)|
1451
+ |[openmoss/MOVA-360p](https://modelscope.cn/models/openmoss/MOVA-360p)|`input_image`|[code](/examples/mova/model_inference/MOVA-360p-I2AV.py)|[code](/examples/mova/model_inference_low_vram/MOVA-360p-I2AV.py)|[code](/examples/mova/model_training/full/MOVA-360P-I2AV.sh)|[code](/examples/mova/model_training/validate_full/MOVA-360p-I2AV.py)|[code](/examples/mova/model_training/lora/MOVA-360P-I2AV.sh)|[code](/examples/mova/model_training/validate_lora/MOVA-360p-I2AV.py)|
1452
+ |[openmoss/MOVA-720p](https://modelscope.cn/models/openmoss/MOVA-720p)|`input_image`|[code](/examples/mova/model_inference/MOVA-720p-I2AV.py)|[code](/examples/mova/model_inference_low_vram/MOVA-720p-I2AV.py)|[code](/examples/mova/model_training/full/MOVA-720P-I2AV.sh)|[code](/examples/mova/model_training/validate_full/MOVA-720p-I2AV.py)|[code](/examples/mova/model_training/lora/MOVA-720P-I2AV.sh)|[code](/examples/mova/model_training/validate_lora/MOVA-720p-I2AV.py)|
1453
+ |[Wan-AI/Wan-Dancer-14B (global model)](https://modelscope.cn/models/Wan-AI/Wan-Dancer-14B)|`wantodance_music_path`, `wantodance_reference_image`, `wantodance_fps`, `wantodance_keyframes`, `wantodance_keyframes_mask`|[code](/examples/wanvideo/model_inference/Wan-Dancer-14B-global.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan-Dancer-14B-global.py)|[code](/examples/wanvideo/model_training/full/Wan-Dancer-14B-global.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan-Dancer-14B-global.py)|[code](/examples/wanvideo/model_training/lora/Wan-Dancer-14B-global.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan-Dancer-14B-global.py)|
1454
+ |[Wan-AI/Wan-Dancer-14B (local model)](https://modelscope.cn/models/Wan-AI/Wan-Dancer-14B)|`wantodance_music_path`, `wantodance_reference_image`, `wantodance_fps`, `wantodance_keyframes`, `wantodance_keyframes_mask`|[code](/examples/wanvideo/model_inference/Wan-Dancer-14B-local.py)|[code](/examples/wanvideo/model_inference_low_vram/Wan-Dancer-14B-local.py)|[code](/examples/wanvideo/model_training/full/Wan-Dancer-14B-local.sh)|[code](/examples/wanvideo/model_training/validate_full/Wan-Dancer-14B-local.py)|[code](/examples/wanvideo/model_training/lora/Wan-Dancer-14B-local.sh)|[code](/examples/wanvideo/model_training/validate_lora/Wan-Dancer-14B-local.py)|
1451
1455
 
1452
1456
  </details>
1453
1457
 
@@ -1586,6 +1590,7 @@ Example code for MiniMax-H3 is available at: [/examples/minimax_h3/](/examples/m
1586
1590
  |-|-|-|-|-|-|-|
1587
1591
  |[MiniMax/MiniMax-H3: FL2VA](https://www.modelscope.cn/models/MiniMax/MiniMax-H3)|[code](/examples/minimax_h3/model_inference/MiniMax-H3-FL2VA.py)|[code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-FL2VA.py)|[code](/examples/minimax_h3/model_training/full/MiniMax-H3-FL2VA.sh)|[code](/examples/minimax_h3/model_training/validate_full/MiniMax-H3-FL2VA.py)|[code](/examples/minimax_h3/model_training/lora/MiniMax-H3-FL2VA.sh)|[code](/examples/minimax_h3/model_training/validate_lora/MiniMax-H3-FL2VA.py)|
1588
1592
  |[MiniMax/MiniMax-H3: Ref2VA](https://www.modelscope.cn/models/MiniMax/MiniMax-H3)|[code](/examples/minimax_h3/model_inference/MiniMax-H3-Ref2VA.py)|[code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-Ref2VA.py)|[code](/examples/minimax_h3/model_training/full/MiniMax-H3-Ref2VA.sh)|[code](/examples/minimax_h3/model_training/validate_full/MiniMax-H3-Ref2VA.py)|[code](/examples/minimax_h3/model_training/lora/MiniMax-H3-Ref2VA.sh)|[code](/examples/minimax_h3/model_training/validate_lora/MiniMax-H3-Ref2VA.py)|
1593
+ |[MiniMax/MiniMax-H3: Retake](https://www.modelscope.cn/models/MiniMax/MiniMax-H3)|[code](/examples/minimax_h3/model_inference/MiniMax-H3-Retake.py)|[code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-Retake.py)|-|-|-|-|
1589
1594
  |[DiffSynth-Studio/MiniMax-H3-NF4: FL2VA](https://www.modelscope.cn/models/DiffSynth-Studio/MiniMax-H3-NF4)|[code](/examples/minimax_h3/model_inference/MiniMax-H3-NF4-FL2VA.py)|[code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-NF4-FL2VA.py)|-|-|[code](/examples/minimax_h3/model_training/lora/MiniMax-H3-NF4-FL2VA.sh)|[code](/examples/minimax_h3/model_training/validate_lora/MiniMax-H3-NF4-FL2VA.py)|
1590
1595
  |[DiffSynth-Studio/MiniMax-H3-NF4: Ref2VA](https://www.modelscope.cn/models/DiffSynth-Studio/MiniMax-H3-NF4)|[code](/examples/minimax_h3/model_inference/MiniMax-H3-NF4-Ref2VA.py)|[code](/examples/minimax_h3/model_inference_low_vram/MiniMax-H3-NF4-Ref2VA.py)|-|-|[code](/examples/minimax_h3/model_training/lora/MiniMax-H3-NF4-Ref2VA.sh)|[code](/examples/minimax_h3/model_training/validate_lora/MiniMax-H3-NF4-Ref2VA.py)|
1591
1596
 
@@ -81,6 +81,13 @@ qwen_image_series = [
81
81
  ]
82
82
 
83
83
  wan_series = [
84
+ {
85
+ # Example: ModelConfig(model_id="Wan-AI/Wan2.2-Animate-2-14B", origin_file_pattern="wan_animate_2/wan_animate_2_bf16.safetensors")
86
+ "model_hash": "4536c21ad8740ba78367af4216ae85bf",
87
+ "model_name": "wan_video_dit",
88
+ "model_class": "diffsynth.models.wan_animate_2_dit.WanAnimate2Transformer",
89
+ "extra_kwargs": {},
90
+ },
84
91
  {
85
92
  # Example: ModelConfig(model_id="krea/krea-realtime-video", origin_file_pattern="krea-realtime-video-14b.safetensors")
86
93
  "model_hash": "5ec04e02b42d2580483ad69f4e76346a",
@@ -114,6 +114,15 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
114
114
  "diffsynth.models.wan_video_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
115
115
  "torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
116
116
  },
117
+ "diffsynth.models.wan_animate_2_dit.WanAnimate2Transformer": {
118
+ "diffsynth.models.wan_video_dit.MLP": "diffsynth.core.vram.layers.AutoWrappedModule",
119
+ "diffsynth.models.wan_animate_2_dit.AttentionBlock": "diffsynth.core.vram.layers.AutoWrappedNonRecurseModule",
120
+ "diffsynth.models.wan_animate_2_dit.Head": "diffsynth.core.vram.layers.AutoWrappedModule",
121
+ "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
122
+ "torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
123
+ "torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
124
+ "diffsynth.models.wan_video_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
125
+ },
117
126
  "diffsynth.models.wan_video_dit.WanModel": {
118
127
  "diffsynth.models.wan_video_dit.MLP": "diffsynth.core.vram.layers.AutoWrappedModule",
119
128
  "diffsynth.models.wan_video_dit.DiTBlock": "diffsynth.core.vram.layers.AutoWrappedNonRecurseModule",
@@ -1,6 +1,11 @@
1
1
  import torch, os, inspect
2
2
  from einops import rearrange, repeat
3
3
 
4
+ try:
5
+ from flash_attn.cute import flash_attn_func as flash_attn_func_cute
6
+ FLASH_ATTN_4_AVAILABLE = True
7
+ except ModuleNotFoundError:
8
+ FLASH_ATTN_4_AVAILABLE = False
4
9
 
5
10
  try:
6
11
  import flash_attn_interface
@@ -26,6 +31,13 @@ try:
26
31
  except ModuleNotFoundError:
27
32
  XFORMERS_AVAILABLE = False
28
33
 
34
+ try:
35
+ from torch.nn.attention.flex_attention import flex_attention as flex_attention_func
36
+ flex_attention_func = torch.compile(flex_attention_func, dynamic=False, mode="max-autotune-no-cudagraphs", fullgraph=True, backend="inductor")
37
+ FLEX_ATTN_AVAILABLE = True
38
+ except (ModuleNotFoundError, ImportError):
39
+ FLEX_ATTN_AVAILABLE = False
40
+
29
41
  try:
30
42
  if "enable_gqa" in inspect.signature(torch.nn.functional.scaled_dot_product_attention).parameters:
31
43
  TORCH_SUPPORT_GQA = True
@@ -38,6 +50,8 @@ except:
38
50
  def initialize_attention_priority():
39
51
  if os.environ.get('DIFFSYNTH_ATTENTION_IMPLEMENTATION') is not None:
40
52
  return os.environ.get('DIFFSYNTH_ATTENTION_IMPLEMENTATION').lower()
53
+ elif FLASH_ATTN_4_AVAILABLE:
54
+ return "flash_attention_4"
41
55
  elif FLASH_ATTN_3_AVAILABLE:
42
56
  return "flash_attention_3"
43
57
  elif FLASH_ATTN_2_AVAILABLE:
@@ -133,11 +147,22 @@ def torch_sdpa_sliding_window(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor,
133
147
  return output
134
148
 
135
149
 
150
+ def flash_attention_4(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s d", out_pattern="b n s d", dims=None, scale=None, is_causal=False, window_size=None):
151
+ required_in_pattern, required_out_pattern= "b s n d", "b s n d"
152
+ q, k, v = rearrange_qkv(q, k, v, q_pattern, k_pattern, v_pattern, required_in_pattern, dims)
153
+ window_size = (window_size, window_size) if window_size is not None else (-1, -1)
154
+ out = flash_attn_func_cute(q, k, v, softmax_scale=scale, causal=is_causal, window_size=window_size)
155
+ if isinstance(out, tuple):
156
+ out = out[0]
157
+ out = rearrange_out(out, out_pattern, required_out_pattern, dims)
158
+ return out
159
+
160
+
136
161
  def flash_attention_3(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s d", out_pattern="b n s d", dims=None, scale=None, is_causal=False, window_size=None):
137
162
  required_in_pattern, required_out_pattern= "b s n d", "b s n d"
138
163
  q, k, v = rearrange_qkv(q, k, v, q_pattern, k_pattern, v_pattern, required_in_pattern, dims)
139
164
  window_size = (window_size, window_size) if window_size is not None else (-1, -1)
140
- out = flash_attn_interface.flash_attn_func(q, k, v, softmax_scale=scale, window_size=window_size)
165
+ out = flash_attn_interface.flash_attn_func(q, k, v, softmax_scale=scale, causal=is_causal, window_size=window_size)
141
166
  if isinstance(out, tuple):
142
167
  out = out[0]
143
168
  out = rearrange_out(out, out_pattern, required_out_pattern, dims)
@@ -169,14 +194,27 @@ def xformers_attention(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_patt
169
194
  return out
170
195
 
171
196
 
172
- def attention_forward(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s d", out_pattern="b n s d", dims=None, attn_mask=None, scale=None, is_causal=False, compatibility_mode=False, window_size=None):
197
+ def flex_attention(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s d", out_pattern="b n s d", dims=None, attn_mask=None, scale=None, score_mod=None):
198
+ assert FLEX_ATTN_AVAILABLE, "Flex Attention is not available. Please upgrade torch to 2.5.0 or later."
199
+ required_in_pattern, required_out_pattern = "b n s d", "b n s d"
200
+ q, k, v = rearrange_qkv(q, k, v, q_pattern, k_pattern, v_pattern, required_in_pattern, dims)
201
+ out = flex_attention_func(query=q, key=k, value=v, block_mask=attn_mask, scale=scale, score_mod=score_mod)
202
+ out = rearrange_out(out, out_pattern, required_out_pattern, dims)
203
+ return out
204
+
205
+
206
+ def attention_forward(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s d", out_pattern="b n s d", dims=None, attn_mask=None, scale=None, is_causal=False, compatibility_mode=False, window_size=None, use_flex=False, score_mod=None):
173
207
  if compatibility_mode or (attn_mask is not None) or ATTENTION_IMPLEMENTATION == "torch":
174
- if window_size is None:
208
+ if use_flex or score_mod is not None:
209
+ return flex_attention(q, k, v, q_pattern, k_pattern, v_pattern, out_pattern, dims, attn_mask=attn_mask, scale=scale, score_mod=score_mod)
210
+ elif window_size is None:
175
211
  return torch_sdpa(q, k, v, q_pattern, k_pattern, v_pattern, out_pattern, dims, attn_mask=attn_mask, scale=scale, is_causal=is_causal)
176
212
  else:
177
213
  # Sliding Window Attention is not compatible with `is_causal` and `attn_mask`.
178
214
  assert is_causal == False and attn_mask is None
179
215
  return torch_sdpa_sliding_window(q, k, v, window_size, q_pattern, k_pattern, v_pattern, out_pattern, dims, scale=scale)
216
+ elif ATTENTION_IMPLEMENTATION == "flash_attention_4":
217
+ return flash_attention_4(q, k, v, q_pattern, k_pattern, v_pattern, out_pattern, dims, scale=scale, is_causal=is_causal, window_size=window_size)
180
218
  elif ATTENTION_IMPLEMENTATION == "flash_attention_3":
181
219
  return flash_attention_3(q, k, v, q_pattern, k_pattern, v_pattern, out_pattern, dims, scale=scale, is_causal=is_causal, window_size=window_size)
182
220
  elif ATTENTION_IMPLEMENTATION == "flash_attention_2":
@@ -357,10 +357,11 @@ class AutoWrappedLinear(torch.nn.Linear, AutoTorchModule, LoRAHotLoadMixin):
357
357
  input = input / (scale_a + 1e-8)
358
358
  input = input.to(self.computation_dtype)
359
359
  weight = weight.to(self.computation_dtype)
360
- bias = bias.to(torch.bfloat16)
360
+ if bias is not None:
361
+ bias = bias.to(torch.bfloat16)
361
362
 
362
363
  result = torch._scaled_mm(
363
- input,
364
+ input.to(self.computation_dtype),
364
365
  weight.T,
365
366
  scale_a=scale_a,
366
367
  scale_b=scale_b.T,
@@ -302,7 +302,7 @@ class FlowMatchScheduler():
302
302
  return sigmas, timesteps
303
303
 
304
304
  @staticmethod
305
- def set_timesteps_minimax_h3(num_inference_steps=50, denoising_strength=1.0, shift=12.0):
305
+ def set_timesteps_minimax_h3(num_inference_steps=50, denoising_strength=1.0, shift=2.22):
306
306
  num_train_timesteps = 1000
307
307
  base = torch.linspace(denoising_strength, 0.0, num_inference_steps+1, dtype=torch.float32)[:-1]
308
308
  sigmas = shift * base / (1 + (shift - 1) * base)
@@ -68,30 +68,31 @@ def FlowMatchSFTMiniMaxH3AudioVideoLoss(pipe: BasePipeline, **inputs):
68
68
  min_timestep_boundary = int(inputs.get("min_timestep_boundary", 0) * len(pipe.scheduler.timesteps))
69
69
 
70
70
  timestep_id = torch.randint(min_timestep_boundary, max_timestep_boundary, (1,))
71
- timestep_video = pipe.scheduler.timesteps[timestep_id].to(dtype=pipe.torch_dtype, device=pipe.device)
72
- timestep_audio = pipe.scheduler_audio.timesteps[timestep_id].to(dtype=pipe.torch_dtype, device=pipe.device)
71
+ timestep_video = pipe.scheduler.timesteps[timestep_id].to(dtype=torch.float32, device=pipe.device)
72
+ timestep_audio = pipe.scheduler_audio.timesteps[timestep_id].to(dtype=torch.float32, device=pipe.device)
73
73
 
74
74
  noise = torch.randn_like(inputs["input_latents"])
75
75
  inputs["video_latents"] = pipe.scheduler.add_noise(inputs["input_latents"], noise, timestep_video)
76
76
  training_target = pipe.scheduler.training_target(inputs["input_latents"], noise, timestep_video)
77
77
 
78
- audio_noise = torch.randn_like(inputs["audio_input_latents"])
79
- inputs["audio_latents"] = pipe.scheduler_audio.add_noise(inputs["audio_input_latents"], audio_noise, timestep_audio)
80
- training_target_audio = pipe.scheduler_audio.training_target(inputs["audio_input_latents"], audio_noise, timestep_audio)
78
+ if "audio_input_latents" in inputs:
79
+ audio_noise = torch.randn_like(inputs["audio_input_latents"])
80
+ inputs["audio_latents"] = pipe.scheduler_audio.add_noise(inputs["audio_input_latents"], audio_noise, timestep_audio)
81
+ training_target_audio = pipe.scheduler_audio.training_target(inputs["audio_input_latents"], audio_noise, timestep_audio)
81
82
 
82
83
  models = {name: getattr(pipe, name) for name in pipe.in_iteration_models}
83
84
  noise_pred, noise_pred_audio = pipe.model_fn(
84
85
  **models, **inputs,
85
- t_video=1.0 - float(timestep_video) / pipe.scheduler.num_train_timesteps,
86
- t_audio=1.0 - float(timestep_audio) / pipe.scheduler_audio.num_train_timesteps,
87
- device=pipe.device,
86
+ timestep_video=timestep_video, timestep_audio=timestep_audio,
88
87
  )
89
88
 
90
89
  loss = torch.nn.functional.mse_loss(noise_pred.float(), training_target.float())
91
90
  loss = loss * pipe.scheduler.training_weight(timestep_video)
92
- loss_audio = torch.nn.functional.mse_loss(noise_pred_audio.float(), training_target_audio.float())
93
- loss_audio = loss_audio * pipe.scheduler_audio.training_weight(timestep_audio)
94
- return loss + loss_audio
91
+ if "audio_input_latents" in inputs:
92
+ loss_audio = torch.nn.functional.mse_loss(noise_pred_audio.float(), training_target_audio.float())
93
+ loss_audio = loss_audio * pipe.scheduler_audio.training_weight(timestep_audio)
94
+ loss = loss + loss_audio
95
+ return loss
95
96
 
96
97
 
97
98
  def DirectDistillLoss(pipe: BasePipeline, **inputs):
@@ -21,11 +21,12 @@ def patchify_video(latent: torch.Tensor) -> torch.Tensor:
21
21
  return packed.reshape(b * t * h * w, c * _PATCH_T * _PATCH_H * _PATCH_W).contiguous()
22
22
 
23
23
 
24
- def unpatchify_video(rows: torch.Tensor, t: int, h: int, w: int, channel: int = 24) -> torch.Tensor:
25
- # [T*h*w, 96] -> [1,24,T,h*2,w*2] (inverse of patchify_video; h,w are patched dims)
24
+ def unpatchify_video(rows: torch.Tensor, ft: int, fh: int, fw: int, channel: int = 24) -> torch.Tensor:
25
+ # [T*(H/2)*(W/2), 96] -> [1,24,T,H,W] (inverse of patchify_video; ft/fh/fw match its input)
26
+ t, h, w = ft // _PATCH_T, fh // _PATCH_H, fw // _PATCH_W
26
27
  packed = rows.reshape(-1, t, h, w, channel, _PATCH_T, _PATCH_H, _PATCH_W)
27
28
  latent = torch.einsum("nthwcrpq->nctrhpwq", packed)
28
- return latent.reshape(-1, channel, t * _PATCH_T, h * _PATCH_H, w * _PATCH_W).contiguous()
29
+ return latent.reshape(-1, channel, ft, fh, fw).contiguous()
29
30
 
30
31
 
31
32
  def pack_audio(latent: torch.Tensor) -> torch.Tensor: