diffsynth 2.2.0__py3-none-any.whl → 2.2.1__py3-none-any.whl

diffsynth/configs/model_configs.py

@@ -1743,6 +1743,29 @@ minimax_music3_series = [
     },
 ]
 
+minimax_h3_image_series = [
+    {
+        # Example: ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="transformer/model*.safetensors")
+        # Example: ModelConfig(path="./models/train/MiniMax-H3-Image-full-split/epoch-4.safetensors")
+        "model_hash": "cbc654a2ff91b53b57e2556904bdbc5e",
+        "model_name": "minimax_h3_image_dit",
+        "model_class": "diffsynth.models.minimax_h3_image_dit.MiniMaxH3ImageDiT",
+    },
+    {
+        # Example: ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="pdd_fused_heads.safetensors")
+        "model_hash": "af836167abebf4a4701ab436f291a972",
+        "model_name": "minimax_h3_image_pdd_heads",
+        "model_class": "diffsynth.models.minimax_h3_image_dit.MiniMaxH3ImagePDDHeads",
+    },
+    {
+        # Example: ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
+        "model_hash": "e16b57e3180a14235ffcaad014ce2772",
+        "model_name": "minimax_h3_image_vae",
+        "model_class": "diffsynth.models.minimax_h3_image_vae.MiniMaxH3ImageVAE",
+        "state_dict_converter": "diffsynth.utils.state_dict_converters.minimax_h3_image_vae.MiniMaxH3ImageVAEStateDictConverter",
+    },
+]
+
 sensenova_u1_series = [
     {
         # Example: ModelConfig(model_id="SenseNova/SenseNova-U1.5-8B-MoT", origin_file_pattern="model*.safetensors")
@@ -1857,5 +1880,5 @@ MODEL_CONFIGS = (
     stable_diffusion_xl_series + stable_diffusion_series + qwen_image_series + qwen_video_edit_series + wan_series + flux_series + flux2_series + ernie_image_series
     + z_image_series + ltx2_series + anima_series + mova_series + joyai_image_series + boogu_image_series + ace_step_series + hidream_o1_image_series
     + image_metrics_series + ideogram4_series + krea2_series + lingbot_video_series + minimax_h3_series + minimax_music3_series + sensenova_u1_series
-    + yue2_series + qwen_image_21_series + flux3_series + moss_image_series + fibo_series
+    + yue2_series + qwen_image_21_series + flux3_series + moss_image_series + fibo_series + minimax_h3_image_series
 )

diffsynth/configs/vram_management_module_maps.py

@@ -10,6 +10,24 @@ flux_general_vram_config = {
 }
 
 VRAM_MANAGEMENT_MODULE_MAPS = {
+    "diffsynth.models.minimax_h3_image_dit.MiniMaxH3ImageDiT": {
+        "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
+        "torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+    },
+    "diffsynth.models.minimax_h3_image_dit.MiniMaxH3ImagePDDHeads": {
+        "diffsynth.models.minimax_h3_image_dit._MiniMaxH3ImagePDDHeadParameters": "diffsynth.core.vram.layers.AutoWrappedModule",
+    },
+    "diffsynth.models.minimax_h3_image_vae.MiniMaxH3ImageVAE": {
+        "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
+        "torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "torch.nn.GroupNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.minimax_h3_video_vae.BaseConv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.minimax_h3_video_vae.WarpedTensor": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.minimax_h3_video_vae.TemporalIsolatedSpatialGroupNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+    },
     "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT": {
         "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
         "torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
@@ -115,6 +133,9 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
         "diffsynth.models.wan_video_animate_adapter.ConvLayer": "diffsynth.core.vram.layers.AutoWrappedModule",
         "diffsynth.models.wan_video_animate_adapter.FusedLeakyReLU": "diffsynth.core.vram.layers.AutoWrappedModule",
         "diffsynth.models.wan_video_animate_adapter.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.wan_video_animate_adapter.Blur": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.wan_video_animate_adapter.EqualConv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "diffsynth.models.wan_video_animate_adapter.Direction": "diffsynth.core.vram.layers.AutoWrappedModule",
         "torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
         "torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
         "torch.nn.Conv1d": "diffsynth.core.vram.layers.AutoWrappedModule",
@@ -150,6 +171,7 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
         "torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
         "diffsynth.models.wan_video_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
         "torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
+        "torch.nn.MultiheadAttention": "diffsynth.core.vram.layers.AutoWrappedModule",
     },
     "diffsynth.models.wan_video_image_encoder.WanImageEncoder": {
         "diffsynth.models.wan_video_image_encoder.VisionTransformer": "diffsynth.core.vram.layers.AutoWrappedModule",

diffsynth/core/attention/attention.py

@@ -15,7 +15,7 @@ def initialize_attention_priority():
     if os.environ.get('DIFFSYNTH_ATTENTION_IMPLEMENTATION') is not None:
         return os.environ.get('DIFFSYNTH_ATTENTION_IMPLEMENTATION').strip().lower()
     else:
-        for name in ["customized_fa_kernel", "flash_attention_4", "flash_attention_3", "flash_attention_2", "sage_attention", "xformers"]:
+        for name in ["customized_fa_kernel", "flash_attention_4", "flash_attention_3", "flash_attention_2", "xformers"]:
             if name in list_attention_implementations():
                 return name
         return "torch"

diffsynth/core/quant/backends/entropack.py

@@ -45,13 +45,13 @@ if ENTROPACK_AVAILABLE:
     @dataclass
     class EntroPackINT8CodedConfig(BackendConfig, ep.LatticeRANSConfig):
         linear_cls = ep.CompressedINT8Linear
-        use_convrot: bool = False
+        use_convrot: bool = True
         convrot_groupsize: int = 256
 
     @dataclass
     class EntroPackINT8RawConfig(BackendConfig, ep.RawConfig):
         linear_cls = ep.CompressedINT8Linear
-        use_convrot: bool = False
+        use_convrot: bool = True
         convrot_groupsize: int = 256