support eligenv2 and context_control

Author: mi804

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

@@ -467,13 +467,17 @@ def process_entity_masks(self, latents, prompt_emb, prompt_emb_mask, entity_prom
         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):
             prompt_start = cumsum[i]
             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 @@ def process_entity_masks(self, latents, prompt_emb, prompt_emb_mask, entity_prom
         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 @@ def __init__(self, device="cuda", torch_dtype=torch.bfloat16):
             QwenImageUnit_InputImageEmbedder(),
             QwenImageUnit_Inpaint(),
             QwenImageUnit_EditImageEmbedder(),
+            QwenImageUnit_ContextImageEmbedder(),
             QwenImageUnit_PromptEmbedder(),
             QwenImageUnit_EntityControl(),
             QwenImageUnit_BlockwiseControlNet(),
@@ -284,6 +285,8 @@ def __call__(
         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 @@ def __call__(
             "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 @@ def process(self, pipe: QwenImagePipeline, edit_image, tiled, tile_size, tile_st
         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)