theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-04-16 15:28:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support JoyAI-Image-Edit (#1393)

Browse Source 
* auto intergrate joyimage model

* joyimage pipeline

* train

* ready

* styling

* joyai-image docs

* update readme

* pr review
This commit is contained in:
Hong Zhang
2026-04-15 16:57:11 +08:00
committed by GitHub
parent 8f18e24597
commit 079e51c9f3
21 changed files with 2040 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
diffsynth/configs/model_configs.py
View File

@@ -900,4 +900,20 @@ mova_series = [
"model_class": "diffsynth.models.mova_dual_tower_bridge.DualTowerConditionalBridge",
},
]
MODEL_CONFIGS = qwen_image_series + wan_series + flux_series + flux2_series + ernie_image_series + z_image_series + ltx2_series + anima_series + mova_series
joyai_image_series = [
{
# Example: ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="transformer/transformer.pth")
"model_hash": "56592ddfd7d0249d3aa527d24161a863",
"model_name": "joyai_image_dit",
"model_class": "diffsynth.models.joyai_image_dit.JoyAIImageDiT",
},
{
# Example: ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="JoyAI-Image-Und/model-*.safetensors")
"model_hash": "2d11bf14bba8b4e87477c8199a895403",
"model_name": "joyai_image_text_encoder",
"model_class": "diffsynth.models.joyai_image_text_encoder.JoyAIImageTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.joyai_image_text_encoder.JoyAIImageTextEncoderStateDictConverter",
},
]
MODEL_CONFIGS = qwen_image_series + wan_series + flux_series + flux2_series + ernie_image_series + z_image_series + ltx2_series + anima_series + mova_series + joyai_image_series

16
diffsynth/configs/vram_management_module_maps.py
View File

@@ -279,6 +279,22 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
"torch.nn.Embedding": "diffsynth.core.vram.layers.AutoWrappedModule",
"transformers.models.ministral3.modeling_ministral3.Ministral3RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.joyai_image_dit.Transformer3DModel": {
"diffsynth.models.joyai_image_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"diffsynth.models.joyai_image_dit.ModulateWan": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.joyai_image_text_encoder.JoyAIImageTextEncoder": {
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"torch.nn.Embedding": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
"transformers.models.qwen3_vl.modeling_qwen3_vl.Qwen3VLVisionModel": "diffsynth.core.vram.layers.AutoWrappedModule",
"transformers.models.qwen3_vl.modeling_qwen3_vl.Qwen3VLTextRMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"transformers.models.qwen3_vl.modeling_qwen3_vl.Qwen3VLTextRotaryEmbedding": "diffsynth.core.vram.layers.AutoWrappedModule",
},
}
def QwenImageTextEncoder_Module_Map_Updater():