support eligenv2 and context_control

README.md

@@ -91,12 +91,14 @@ image.save("image.jpg")
 |-|-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./examples/qwen_image/model_inference/Qwen-Image.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image.py)|
 |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)|
+|[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|
+|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py)|
 |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
 
 </details>
@@ -370,6 +372,10 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 
 
 ## Update History
+- **August 21, 2025**: [DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control) is released! Compared to the V1 version, the training dataset has been updated to the [Qwen-Image-Self-Generated-Dataset](https://www.modelscope.cn/datasets/DiffSynth-Studio/Qwen-Image-Self-Generated-Dataset), enabling generated images to better align with the inherent image distribution and style of Qwen-Image. Please refer to [our sample code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py).
+
+- **August 21, 2025**: We open-sourced the [DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control) structure control LoRA model. Following "In Context" routine, it supports various types of structural control conditions, including canny, depth, lineart, softedge, normal, and openpose. Please refer to [our sample code](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py).
+
 - **August 20, 2025** We open-sourced [DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix), which improves the editing performance of Qwen-Image-Edit on low-resolution image inputs. Please refer to [our example code](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py).
 
 - **August 19, 2025** 🔥 Qwen-Image-Edit is now open source. Welcome the new member to the image editing model family!

README_zh.md

@@ -93,12 +93,14 @@ image.save("image.jpg")
 |-|-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./examples/qwen_image/model_inference/Qwen-Image.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image.py)|
 |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)|
+|[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|
+|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py)|
 |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
 
 </details>
@@ -386,6 +388,10 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44
 
 
 ## 更新历史
+- **2025年8月21日** [DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control) 发布！相比于 V1 版本，训练数据集变为 [Qwen-Image-Self-Generated-Dataset](https://www.modelscope.cn/datasets/DiffSynth-Studio/Qwen-Image-Self-Generated-Dataset)，因此，生成的图像更符合 Qwen-Image 本身的图像分布和风格。 请参考[我们的示例代码](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)。
+
+- **2025年8月21日** 我们开源了 [DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control) 结构控制 LoRA 模型，采用 In Context 的技术路线，支持多种类别的结构控制条件，包括 canny, depth, lineart, softedge, normal, openpose。 请参考[我们的示例代码](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py)。
+
 - **2025年8月20日** 我们开源了 [DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix) 模型，提升了 Qwen-Image-Edit 对低分辨率图像输入的编辑效果。请参考[我们的示例代码](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py)
 
 - **2025年8月19日** 🔥 Qwen-Image-Edit 开源，欢迎图像编辑模型新成员！

diffsynth/models/qwen_image_dit.py

@@ -467,6 +467,7 @@ class QwenImageDiT(torch.nn.Module):
         image_start = sum(seq_lens)
         image_end = total_seq_len
         cumsum = [0]
+        single_image_seq = image_end - image_start
         for length in seq_lens:
             cumsum.append(cumsum[-1] + length)
         for i in range(N):
@@ -474,6 +475,9 @@ class QwenImageDiT(torch.nn.Module):
             prompt_end = cumsum[i+1]
             image_mask = torch.sum(patched_masks[i], dim=-1) > 0
             image_mask = image_mask.unsqueeze(1).repeat(1, seq_lens[i], 1)
+            # repeat image mask to match the single image sequence length
+            repeat_time = single_image_seq // image_mask.shape[-1]
+            image_mask = image_mask.repeat(1, 1, repeat_time)
             # prompt update with image
             attention_mask[:, prompt_start:prompt_end, image_start:image_end] = image_mask
             # image update with prompt
@@ -493,7 +497,8 @@ class QwenImageDiT(torch.nn.Module):
         attention_mask = attention_mask.to(device=latents.device, dtype=latents.dtype).unsqueeze(1)
 
         return all_prompt_emb, image_rotary_emb, attention_mask
-        
+
+
     def forward(
         self,
         latents=None,

diffsynth/pipelines/qwen_image.py

@@ -69,6 +69,7 @@ class QwenImagePipeline(BasePipeline):
             QwenImageUnit_InputImageEmbedder(),
             QwenImageUnit_Inpaint(),
             QwenImageUnit_EditImageEmbedder(),
+            QwenImageUnit_ContextImageEmbedder(),
             QwenImageUnit_PromptEmbedder(),
             QwenImageUnit_EntityControl(),
             QwenImageUnit_BlockwiseControlNet(),
@@ -284,6 +285,8 @@ class QwenImagePipeline(BasePipeline):
         edit_image: Image.Image = None,
         edit_image_auto_resize: bool = True,
         edit_rope_interpolation: bool = False,
+        # Qwen-Image-Context-Control
+        context_image: Image.Image = None,
         # FP8
         enable_fp8_attention: bool = False,
         # Tile
@@ -315,6 +318,7 @@ class QwenImagePipeline(BasePipeline):
             "tiled": tiled, "tile_size": tile_size, "tile_stride": tile_stride,
             "eligen_entity_prompts": eligen_entity_prompts, "eligen_entity_masks": eligen_entity_masks, "eligen_enable_on_negative": eligen_enable_on_negative,
             "edit_image": edit_image, "edit_image_auto_resize": edit_image_auto_resize, "edit_rope_interpolation": edit_rope_interpolation, 
+            "context_image": context_image,
         }
         for unit in self.units:
             inputs_shared, inputs_posi, inputs_nega = self.unit_runner(unit, self, inputs_shared, inputs_posi, inputs_nega)
@@ -615,6 +619,21 @@ class QwenImageUnit_EditImageEmbedder(PipelineUnit):
         edit_latents = pipe.vae.encode(edit_image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride)
         return {"edit_latents": edit_latents, "edit_image": resized_edit_image}
 
+class QwenImageUnit_ContextImageEmbedder(PipelineUnit):
+    def __init__(self):
+        super().__init__(
+            input_params=("context_image", "height", "width", "tiled", "tile_size", "tile_stride"),
+            onload_model_names=("vae",)
+        )
+
+    def process(self, pipe: QwenImagePipeline, context_image, height, width, tiled, tile_size, tile_stride):
+        if context_image is None:
+            return {}
+        pipe.load_models_to_device(['vae'])
+        context_image = pipe.preprocess_image(context_image.resize((width, height))).to(device=pipe.device, dtype=pipe.torch_dtype)
+        context_latents = pipe.vae.encode(context_image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride)
+        return {"context_latents": context_latents}
+
 
 def model_fn_qwen_image(
     dit: QwenImageDiT = None,
@@ -633,6 +652,7 @@ def model_fn_qwen_image(
     entity_prompt_emb_mask=None,
     entity_masks=None,
     edit_latents=None,
+    context_latents=None,
     enable_fp8_attention=False,
     use_gradient_checkpointing=False,
     use_gradient_checkpointing_offload=False,
@@ -646,6 +666,10 @@ def model_fn_qwen_image(
     image = rearrange(latents, "B C (H P) (W Q) -> B (H W) (C P Q)", H=height//16, W=width//16, P=2, Q=2)
     image_seq_len = image.shape[1]
 
+    if context_latents is not None:
+        img_shapes += [(context_latents.shape[0], context_latents.shape[2]//2, context_latents.shape[3]//2)]
+        context_image = rearrange(context_latents, "B C (H P) (W Q) -> B (H W) (C P Q)", H=context_latents.shape[2]//2, W=context_latents.shape[3]//2, P=2, Q=2)
+        image = torch.cat([image, context_image], dim=1)
     if edit_latents is not None:
         img_shapes += [(edit_latents.shape[0], edit_latents.shape[2]//2, edit_latents.shape[3]//2)]
         edit_image = rearrange(edit_latents, "B C (H P) (W Q) -> B (H W) (C P Q)", H=edit_latents.shape[2]//2, W=edit_latents.shape[3]//2, P=2, Q=2)
@@ -692,7 +716,7 @@ def model_fn_qwen_image(
     
     image = dit.norm_out(image, conditioning)
     image = dit.proj_out(image)
-    if edit_latents is not None:
+    if edit_latents is not None or context_latents is not None:
         image = image[:, :image_seq_len]
     
     latents = rearrange(image, "B (H W) (C P Q) -> B C (H P) (W Q)", H=height//16, W=width//16, P=2, Q=2)

examples/qwen_image/README.md

@@ -47,9 +47,11 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
+|[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./model_inference/Qwen-Image-EliGen-V2.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|
+|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)|
 |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
 
 ## Model Inference

examples/qwen_image/README_zh.md

@@ -47,9 +47,11 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
+|[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./model_inference/Qwen-Image-EliGen-V2.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|
+|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)|
 |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
 
 ## 模型推理

examples/qwen_image/model_inference/Qwen-Image-Context-Control.py

@@ -0,0 +1,35 @@
+from PIL import Image
+import torch
+from modelscope import dataset_snapshot_download, snapshot_download
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth.controlnets.processors import Annotator
+from diffsynth import download_models
+
+download_models(["Annotators:Depth"])
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", 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"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+snapshot_download("DiffSynth-Studio/Qwen-Image-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors")
+pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors")
+
+dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg")
+origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024))
+annotator_ids = ['openpose', 'canny', 'depth', 'lineart', 'softedge', 'normal']
+for annotator_id in annotator_ids:
+    annotator = Annotator(processor_id=annotator_id, device="cuda")
+    control_image = annotator(origin_image)
+    control_image.save(f"{annotator.processor_id}.png")
+
+    control_prompt = "Context_Control. "
+    prompt = f"{control_prompt}一个穿着淡蓝色的漂亮女孩正在翩翩起舞，背景是梦幻的星空，光影交错，细节精致。"
+    negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
+    image = pipe(prompt, seed=1, negative_prompt=negative_prompt, context_image=control_image, height=1024, width=1024)
+    image.save(f"image_{annotator.processor_id}.png")

examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py

@@ -0,0 +1,106 @@
+import torch
+import random
+from PIL import Image, ImageDraw, ImageFont
+from modelscope import dataset_snapshot_download, snapshot_download
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+
+def visualize_masks(image, masks, mask_prompts, output_path, font_size=35, use_random_colors=False):
+    # Create a blank image for overlays
+    overlay = Image.new('RGBA', image.size, (0, 0, 0, 0))
+
+    colors = [
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+    ]
+    # Generate random colors for each mask
+    if use_random_colors:
+        colors = [(random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), 80) for _ in range(len(masks))]
+
+    # Font settings
+    try:
+        font = ImageFont.truetype("wqy-zenhei.ttc", font_size)  # Adjust as needed
+    except IOError:
+        font = ImageFont.load_default(font_size)
+
+    # Overlay each mask onto the overlay image
+    for mask, mask_prompt, color in zip(masks, mask_prompts, colors):
+        # Convert mask to RGBA mode
+        mask_rgba = mask.convert('RGBA')
+        mask_data = mask_rgba.getdata()
+        new_data = [(color if item[:3] == (255, 255, 255) else (0, 0, 0, 0)) for item in mask_data]
+        mask_rgba.putdata(new_data)
+
+        # Draw the mask prompt text on the mask
+        draw = ImageDraw.Draw(mask_rgba)
+        mask_bbox = mask.getbbox()  # Get the bounding box of the mask
+        text_position = (mask_bbox[0] + 10, mask_bbox[1] + 10)  # Adjust text position based on mask position
+        draw.text(text_position, mask_prompt, fill=(255, 255, 255, 255), font=font)
+
+        # Alpha composite the overlay with this mask
+        overlay = Image.alpha_composite(overlay, mask_rgba)
+
+    # Composite the overlay onto the original image
+    result = Image.alpha_composite(image.convert('RGBA'), overlay)
+
+    # Save or display the resulting image
+    result.save(output_path)
+
+    return result
+
+def example(pipe, seeds, example_id, global_prompt, entity_prompts):
+    dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/eligen/qwen-image/example_{example_id}/*.png")
+    masks = [Image.open(f"./data/examples/eligen/qwen-image/example_{example_id}/{i}.png").convert('RGB').resize((1024, 1024)) for i in range(len(entity_prompts))]
+    negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
+    for seed in seeds:
+        # generate image
+        image = pipe(
+            prompt=global_prompt,
+            cfg_scale=4.0,
+            negative_prompt=negative_prompt,
+            num_inference_steps=40,
+            seed=seed,
+            height=1024,
+            width=1024,
+            eligen_entity_prompts=entity_prompts,
+            eligen_entity_masks=masks,
+        )
+        image.save(f"eligen_example_{example_id}_{seed}.png")
+        visualize_masks(image, masks, entity_prompts, f"eligen_example_{example_id}_mask_{seed}.png")
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", 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"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+snapshot_download("DiffSynth-Studio/Qwen-Image-EliGen-V2", local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-V2", allow_file_pattern="model.safetensors")
+pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors")
+
+seeds = [0]
+
+global_prompt = "写实摄影风格. A beautiful asia woman wearing white dress, she is holding a mirror with her right arm, with a beach background."
+entity_prompts = ["A beautiful woman", "mirror", "necklace", "glasses", "earring", "white dress", "jewelry headpiece"]
+example(pipe, seeds, 7, global_prompt, entity_prompts)
+
+global_prompt = "写实摄影风格, 细节丰富。街头一位漂亮的女孩，穿着衬衫和短裤，手持写有“实体控制”的标牌，背景是繁忙的城市街道，阳光明媚，行人匆匆。"
+entity_prompts = ["一个漂亮的女孩", "标牌 '实体控制'", "短裤", "衬衫"]
+example(pipe, seeds, 4, global_prompt, entity_prompts)

examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py

@@ -0,0 +1,36 @@
+from PIL import Image
+import torch
+from modelscope import dataset_snapshot_download, snapshot_download
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth.controlnets.processors import Annotator
+from diffsynth import download_models
+
+download_models(["Annotators:Depth"])
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_dtype=torch.float8_e4m3fn),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.enable_vram_management()
+snapshot_download("DiffSynth-Studio/Qwen-Image-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors")
+pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors")
+
+dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg")
+origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024))
+annotator_ids = ['openpose', 'canny', 'depth', 'lineart', 'softedge', 'normal']
+for annotator_id in annotator_ids:
+    annotator = Annotator(processor_id=annotator_id, device="cuda")
+    control_image = annotator(origin_image)
+    control_image.save(f"{annotator.processor_id}.png")
+
+    control_prompt = "Context_Control. "
+    prompt = f"{control_prompt}一个穿着淡蓝色的漂亮女孩正在翩翩起舞，背景是梦幻的星空，光影交错，细节精致。"
+    negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
+    image = pipe(prompt, seed=1, negative_prompt=negative_prompt, context_image=control_image, height=1024, width=1024)
+    image.save(f"image_{annotator.processor_id}.png")

examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py

@@ -0,0 +1,108 @@
+import torch
+import random
+from PIL import Image, ImageDraw, ImageFont
+from modelscope import dataset_snapshot_download, snapshot_download
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+
+
+def visualize_masks(image, masks, mask_prompts, output_path, font_size=35, use_random_colors=False):
+    # Create a blank image for overlays
+    overlay = Image.new('RGBA', image.size, (0, 0, 0, 0))
+
+    colors = [
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+    ]
+    # Generate random colors for each mask
+    if use_random_colors:
+        colors = [(random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), 80) for _ in range(len(masks))]
+
+    # Font settings
+    try:
+        font = ImageFont.truetype("wqy-zenhei.ttc", font_size)  # Adjust as needed
+    except IOError:
+        font = ImageFont.load_default(font_size)
+
+    # Overlay each mask onto the overlay image
+    for mask, mask_prompt, color in zip(masks, mask_prompts, colors):
+        # Convert mask to RGBA mode
+        mask_rgba = mask.convert('RGBA')
+        mask_data = mask_rgba.getdata()
+        new_data = [(color if item[:3] == (255, 255, 255) else (0, 0, 0, 0)) for item in mask_data]
+        mask_rgba.putdata(new_data)
+
+        # Draw the mask prompt text on the mask
+        draw = ImageDraw.Draw(mask_rgba)
+        mask_bbox = mask.getbbox()  # Get the bounding box of the mask
+        text_position = (mask_bbox[0] + 10, mask_bbox[1] + 10)  # Adjust text position based on mask position
+        draw.text(text_position, mask_prompt, fill=(255, 255, 255, 255), font=font)
+
+        # Alpha composite the overlay with this mask
+        overlay = Image.alpha_composite(overlay, mask_rgba)
+
+    # Composite the overlay onto the original image
+    result = Image.alpha_composite(image.convert('RGBA'), overlay)
+
+    # Save or display the resulting image
+    result.save(output_path)
+
+    return result
+
+def example(pipe, seeds, example_id, global_prompt, entity_prompts):
+    dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/eligen/qwen-image/example_{example_id}/*.png")
+    masks = [Image.open(f"./data/examples/eligen/qwen-image/example_{example_id}/{i}.png").convert('RGB').resize((1024, 1024)) for i in range(len(entity_prompts))]
+    negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
+    for seed in seeds:
+        # generate image
+        image = pipe(
+            prompt=global_prompt,
+            cfg_scale=4.0,
+            negative_prompt=negative_prompt,
+            num_inference_steps=40,
+            seed=seed,
+            height=1024,
+            width=1024,
+            eligen_entity_prompts=entity_prompts,
+            eligen_entity_masks=masks,
+        )
+        image.save(f"eligen_example_{example_id}_{seed}.png")
+        visualize_masks(image, masks, entity_prompts, f"eligen_example_{example_id}_mask_{seed}.png")
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_dtype=torch.float8_e4m3fn),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.enable_vram_management()
+snapshot_download("DiffSynth-Studio/Qwen-Image-EliGen-V2", local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-V2", allow_file_pattern="model.safetensors")
+pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors")
+
+seeds = [0]
+
+global_prompt = "写实摄影风格. A beautiful asia woman wearing white dress, she is holding a mirror with her right arm, with a beach background."
+entity_prompts = ["A beautiful woman", "mirror", "necklace", "glasses", "earring", "white dress", "jewelry headpiece"]
+example(pipe, seeds, 7, global_prompt, entity_prompts)
+
+global_prompt = "写实摄影风格, 细节丰富。街头一位漂亮的女孩，穿着衬衫和短裤，手持写有“实体控制”的标牌，背景是繁忙的城市街道，阳光明媚，行人匆匆。"
+entity_prompts = ["一个漂亮的女孩", "标牌 '实体控制'", "短裤", "衬衫"]
+example(pipe, seeds, 4, global_prompt, entity_prompts)

examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh

@@ -0,0 +1,20 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path "data/example_image_dataset" \
+  --dataset_metadata_path data/example_image_dataset/metadata_qwenimage_context.csv \
+  --data_file_keys "image,context_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Context-Control_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 64 \
+  --lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors" \
+  --extra_inputs "context_image" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters
+
+# if you want to train from scratch, you can remove the --lora_checkpoint argument

examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py

@@ -0,0 +1,19 @@
+from PIL import Image
+import torch
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", 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"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Context-Control_lora/epoch-4.safetensors")
+image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024))
+prompt = "Context_Control. a dog"
+image = pipe(prompt=prompt, seed=0, context_image=image, height=1024, width=1024)
+image.save("image_context.jpg")