Support JoyAI-Image-Edit (#1393)

* auto intergrate joyimage model

* joyimage pipeline

* train

* ready

* styling

* joyai-image docs

* update readme

* pr review

examples/joyai_image/model_training/validate_lora/JoyAI-Image-Edit.py

@@ -0,0 +1,30 @@
+import torch
+from PIL import Image
+from diffsynth.pipelines.joyai_image import JoyAIImagePipeline, ModelConfig
+
+pipe = JoyAIImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="transformer/transformer.pth"),
+        ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="JoyAI-Image-Und/model*.safetensors"),
+        ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="vae/Wan2.1_VAE.pth"),
+    ],
+    processor_config=ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="JoyAI-Image-Und/"),
+)
+
+pipe.load_lora(pipe.dit, "models/train/JoyAI-Image-Edit-lora/epoch-4.safetensors")
+
+prompt = "将裙子改为粉色"
+edit_image = Image.open("data/diffsynth_example_dataset/joyai_image/JoyAI-Image-Edit/edit/image1.jpg").convert("RGB")
+
+image = pipe(
+    prompt=prompt,
+    edit_image=edit_image,
+    height=1024,
+    width=1024,
+    seed=0,
+    num_inference_steps=30,
+    cfg_scale=5.0,
+)
+image.save("image_lora.jpg")