From 838b8109b11743f530b7c4a78daab61ab2f815d7 Mon Sep 17 00:00:00 2001 From: mi804 <1576993271@qq.com> Date: Tue, 19 Aug 2025 20:15:36 +0800 Subject: [PATCH] support qwen-image-edit lowres fix --- README.md | 5 +- README_zh.md | 3 + diffsynth/models/qwen_image_dit.py | 60 +++++++++++++++++++ diffsynth/pipelines/qwen_image.py | 15 +++-- examples/qwen_image/README.md | 1 + examples/qwen_image/README_zh.md | 1 + .../Qwen-Image-Edit-Lowres-Fix.py | 26 ++++++++ .../Qwen-Image-Edit-Lowres-Fix.py | 28 +++++++++ 8 files changed, 133 insertions(+), 6 deletions(-) create mode 100644 examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py create mode 100644 examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py diff --git a/README.md b/README.md index 5ede036..39aed08 100644 --- a/README.md +++ b/README.md @@ -97,6 +97,7 @@ image.save("image.jpg") |[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-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)|-|-|-|-| @@ -369,8 +370,10 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## Update History +- **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! -- + - **August 18, 2025** We trained and open-sourced the Inpaint ControlNet model for Qwen-Image, [DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint), which adopts a lightweight architectural design. Please refer to [our sample code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py). - **August 15, 2025** We open-sourced the [Qwen-Image-Self-Generated-Dataset](https://www.modelscope.cn/datasets/DiffSynth-Studio/Qwen-Image-Self-Generated-Dataset). This is an image dataset generated using the Qwen-Image model, with a total of 160,000 `1024 x 1024` images. It includes the general, English text rendering, and Chinese text rendering subsets. We provide caption, entity and control images annotations for each image. Developers can use this dataset to train models such as ControlNet and EliGen for the Qwen-Image model. We aim to promote technological development through open-source contributions! diff --git a/README_zh.md b/README_zh.md index 1b90f5b..f15ac6d 100644 --- a/README_zh.md +++ b/README_zh.md @@ -99,6 +99,7 @@ image.save("image.jpg") |[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-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)|-|-|-|-| @@ -385,6 +386,8 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## 更新历史 +- **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！ - **2025年8月18日** 我们训练并开源了 Qwen-Image 的图像重绘 ControlNet 模型 [DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)，模型结构采用了轻量化的设计，请参考[我们的示例代码](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)。 diff --git a/diffsynth/models/qwen_image_dit.py b/diffsynth/models/qwen_image_dit.py index 6ff216b..89d9ff6 100644 --- a/diffsynth/models/qwen_image_dit.py +++ b/diffsynth/models/qwen_image_dit.py @@ -166,6 +166,66 @@ class QwenEmbedRope(nn.Module): return vid_freqs, txt_freqs + def forward_sampling(self, video_fhw, txt_seq_lens, device): + self._expand_pos_freqs_if_needed(video_fhw, txt_seq_lens) + if self.pos_freqs.device != device: + self.pos_freqs = self.pos_freqs.to(device) + self.neg_freqs = self.neg_freqs.to(device) + + vid_freqs = [] + max_vid_index = 0 + for idx, fhw in enumerate(video_fhw): + frame, height, width = fhw + rope_key = f"{idx}_{height}_{width}" + if idx > 0 and f"{0}_{height}_{width}" not in self.rope_cache: + frame_0, height_0, width_0 = video_fhw[0] + + rope_key_0 = f"0_{height_0}_{width_0}" + spatial_freqs_0 = self.rope_cache[rope_key_0].reshape(frame_0, height_0, width_0, -1) + h_indices = torch.linspace(0, height_0 - 1, height).long() + w_indices = torch.linspace(0, width_0 - 1, width).long() + h_grid, w_grid = torch.meshgrid(h_indices, w_indices, indexing='ij') + sampled_rope = spatial_freqs_0[:, h_grid, w_grid, :] + + freqs_pos = self.pos_freqs.split([x // 2 for x in self.axes_dim], dim=1) + freqs_frame = freqs_pos[0][idx : idx + frame].view(frame, 1, 1, -1).expand(frame, height, width, -1) + sampled_rope[:, :, :, :freqs_frame.shape[-1]] = freqs_frame + + seq_lens = frame * height * width + self.rope_cache[rope_key] = sampled_rope.reshape(seq_lens, -1).clone() + if rope_key not in self.rope_cache: + seq_lens = frame * height * width + freqs_pos = self.pos_freqs.split([x // 2 for x in self.axes_dim], dim=1) + freqs_neg = self.neg_freqs.split([x // 2 for x in self.axes_dim], dim=1) + freqs_frame = freqs_pos[0][idx : idx + frame].view(frame, 1, 1, -1).expand(frame, height, width, -1) + if self.scale_rope: + freqs_height = torch.cat( + [freqs_neg[1][-(height - height // 2) :], freqs_pos[1][: height // 2]], dim=0 + ) + freqs_height = freqs_height.view(1, height, 1, -1).expand(frame, height, width, -1) + freqs_width = torch.cat([freqs_neg[2][-(width - width // 2) :], freqs_pos[2][: width // 2]], dim=0) + freqs_width = freqs_width.view(1, 1, width, -1).expand(frame, height, width, -1) + + else: + freqs_height = freqs_pos[1][:height].view(1, height, 1, -1).expand(frame, height, width, -1) + freqs_width = freqs_pos[2][:width].view(1, 1, width, -1).expand(frame, height, width, -1) + + freqs = torch.cat([freqs_frame, freqs_height, freqs_width], dim=-1).reshape(seq_lens, -1) + self.rope_cache[rope_key] = freqs.clone() + vid_freqs.append(self.rope_cache[rope_key].contiguous()) + + if self.scale_rope: + max_vid_index = max(height // 2, width // 2, max_vid_index) + else: + max_vid_index = max(height, width, max_vid_index) + + max_len = max(txt_seq_lens) + txt_freqs = self.pos_freqs[max_vid_index : max_vid_index + max_len, ...] + vid_freqs = torch.cat(vid_freqs, dim=0) + + return vid_freqs, txt_freqs + + class QwenFeedForward(nn.Module): def __init__( self, diff --git a/diffsynth/pipelines/qwen_image.py b/diffsynth/pipelines/qwen_image.py index 94d98cc..d9da07c 100644 --- a/diffsynth/pipelines/qwen_image.py +++ b/diffsynth/pipelines/qwen_image.py @@ -68,10 +68,10 @@ class QwenImagePipeline(BasePipeline): QwenImageUnit_NoiseInitializer(), QwenImageUnit_InputImageEmbedder(), QwenImageUnit_Inpaint(), + QwenImageUnit_EditImageEmbedder(), QwenImageUnit_PromptEmbedder(), QwenImageUnit_EntityControl(), QwenImageUnit_BlockwiseControlNet(), - QwenImageUnit_EditImageEmbedder(), ] self.model_fn = model_fn_qwen_image @@ -280,6 +280,7 @@ class QwenImagePipeline(BasePipeline): eligen_enable_on_negative: bool = False, # Edit Image edit_image: Image.Image = None, + edit_rope_interpolation: bool = False, # FP8 enable_fp8_attention: bool = False, # Tile @@ -310,7 +311,7 @@ class QwenImagePipeline(BasePipeline): "blockwise_controlnet_inputs": blockwise_controlnet_inputs, "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": edit_image, "edit_rope_interpolation": edit_rope_interpolation, } for unit in self.units: inputs_shared, inputs_posi, inputs_nega = self.unit_runner(unit, self, inputs_shared, inputs_posi, inputs_nega) @@ -583,11 +584,11 @@ class QwenImageUnit_BlockwiseControlNet(PipelineUnit): class QwenImageUnit_EditImageEmbedder(PipelineUnit): def __init__(self): super().__init__( - input_params=("edit_image", "height", "width", "tiled", "tile_size", "tile_stride"), + input_params=("edit_image", "tiled", "tile_size", "tile_stride"), onload_model_names=("vae",) ) - def process(self, pipe: QwenImagePipeline, edit_image, height, width, tiled, tile_size, tile_stride): + def process(self, pipe: QwenImagePipeline, edit_image, tiled, tile_size, tile_stride): if edit_image is None: return {} pipe.load_models_to_device(['vae']) @@ -616,6 +617,7 @@ def model_fn_qwen_image( enable_fp8_attention=False, use_gradient_checkpointing=False, use_gradient_checkpointing_offload=False, + edit_rope_interpolation=False, **kwargs ): img_shapes = [(latents.shape[0], latents.shape[2]//2, latents.shape[3]//2)] @@ -640,7 +642,10 @@ def model_fn_qwen_image( ) else: text = dit.txt_in(dit.txt_norm(prompt_emb)) - image_rotary_emb = dit.pos_embed(img_shapes, txt_seq_lens, device=latents.device) + if edit_rope_interpolation: + image_rotary_emb = dit.pos_embed.forward_sampling(img_shapes, txt_seq_lens, device=latents.device) + else: + image_rotary_emb = dit.pos_embed(img_shapes, txt_seq_lens, device=latents.device) attention_mask = None if blockwise_controlnet_conditioning is not None: diff --git a/examples/qwen_image/README.md b/examples/qwen_image/README.md index 4862e6f..594ecc3 100644 --- a/examples/qwen_image/README.md +++ b/examples/qwen_image/README.md @@ -50,6 +50,7 @@ image.save("image.jpg") |[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-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 diff --git a/examples/qwen_image/README_zh.md b/examples/qwen_image/README_zh.md index fa4f183..160c1a7 100644 --- a/examples/qwen_image/README_zh.md +++ b/examples/qwen_image/README_zh.md @@ -50,6 +50,7 @@ image.save("image.jpg") |[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-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 diff --git a/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py b/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py new file mode 100644 index 0000000..df373d8 --- /dev/null +++ b/examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py @@ -0,0 +1,26 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +import torch +from modelscope import snapshot_download + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-Edit", 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=None, + processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"), +) +snapshot_download("DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix", local_dir="models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix", allow_file_pattern="model.safetensors") +pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix/model.safetensors") + +prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。" +image = pipe(prompt=prompt, seed=0, num_inference_steps=40, height=1024, width=768) +image.save("image.jpg") + +prompt = "将裙子变成粉色" +image = image.resize((512, 384)) +image = pipe(prompt, edit_image=image, seed=1, num_inference_steps=40, height=1024, width=768, edit_rope_interpolation=True) +image.save(f"image2.jpg") diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py new file mode 100644 index 0000000..496f80e --- /dev/null +++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py @@ -0,0 +1,28 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +import torch +from modelscope import snapshot_download + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn), + ], + tokenizer_config=None, + processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"), +) +pipe.enable_vram_management() + +snapshot_download("DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix", local_dir="models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix", allow_file_pattern="model.safetensors") +pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix/model.safetensors") + +prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。" +image = pipe(prompt=prompt, seed=0, num_inference_steps=40, height=1024, width=768) +image.save("image.jpg") + +prompt = "将裙子变成粉色" +image = image.resize((512, 384)) +image = pipe(prompt, edit_image=image, seed=1, num_inference_steps=40, height=1024, width=768, edit_rope_interpolation=True) +image.save(f"image2.jpg")