fix wans2v bug and update readme

examples/qwen_image/model_inference/Qwen-Image-Edit-2511-ICEdit.py

@@ -0,0 +1,47 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from modelscope import snapshot_download
+from PIL import Image
+import torch
+
+# Load models
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image-Edit-2511", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+lora = ModelConfig(
+    model_id="DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA",
+    origin_file_pattern="model.safetensors"
+)
+pipe.load_lora(pipe.dit, lora)
+
+# Load images
+snapshot_download(
+    "DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA",
+    local_dir="./data",
+    allow_file_pattern="assets/*"
+)
+edit_image = [
+    Image.open("data/assets/image1_original.png"),
+    Image.open("data/assets/image1_edit_1.png"),
+    Image.open("data/assets/image2_original.png")
+]
+prompt = "Edit image 3 based on the transformation from image 1 to image 2."
+negative_prompt = "泛黄，AI感，不真实，丑陋，油腻的皮肤，异常的肢体，不协调的肢体"
+
+# Generate
+image_4 = pipe(
+    prompt=prompt, negative_prompt=negative_prompt,
+    edit_image=edit_image,
+    seed=1,
+    num_inference_steps=50,
+    height=1280,
+    width=720,
+    zero_cond_t=True,
+)
+image_4.save("image.png")

examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh

@@ -7,6 +7,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --num_frames 81 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "Wan-AI/Wan2.2-S2V-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/model.safetensors,Wan-AI/Wan2.2-S2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-S2V-14B:Wan2.1_VAE.pth" \
+  --audio_processor_path "Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/" \
   --learning_rate 1e-5 \
   --num_epochs 1 \
   --trainable_models "dit" \

examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh

@@ -7,6 +7,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --num_frames 81 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "Wan-AI/Wan2.2-S2V-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/model.safetensors,Wan-AI/Wan2.2-S2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-S2V-14B:Wan2.1_VAE.pth" \
+  --audio_processor_path "Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/" \
   --learning_rate 1e-4 \
   --num_epochs 5 \
   --remove_prefix_in_ckpt "pipe.dit." \

examples/wanvideo/model_training/train.py

@@ -33,7 +33,7 @@ class WanTrainingModule(DiffusionTrainingModule):
         # Load models
         model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, fp8_models=fp8_models, offload_models=offload_models, device=device)
         tokenizer_config = ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/umt5-xxl/") if tokenizer_path is None else ModelConfig(tokenizer_path)
-        audio_processor_config = ModelConfig(model_id="Wan-AI/Wan2.2-S2V-14B", origin_file_pattern="wav2vec2-large-xlsr-53-english/") if audio_processor_path is None else ModelConfig(audio_processor_path)
+        audio_processor_config = self.parse_path_or_model_id(audio_processor_path)
         self.pipe = WanVideoPipeline.from_pretrained(torch_dtype=torch.bfloat16, device=device, model_configs=model_configs, tokenizer_config=tokenizer_config, audio_processor_config=audio_processor_config)
         self.pipe = self.split_pipeline_units(task, self.pipe, trainable_models, lora_base_model)