diff --git a/README.md b/README.md index cb6c923..d7d3752 100644 --- a/README.md +++ b/README.md @@ -766,9 +766,9 @@ DiffSynth-Studio is not just an engineered model framework, but also an incubato - Paper: [Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation ](https://arxiv.org/abs/2602.03208) -- Sample Code: []() +- Sample Code: coming soon -|FLUX|FLUX + SES|Qwen-Image|Qwen-Image + SES| +|FLUX.1-dev|FLUX.1-dev + SES|Qwen-Image|Qwen-Image + SES| |-|-|-|-| |![Image](https://github.com/user-attachments/assets/5be15dc6-2805-4822-b04c-2573fc0f45f0)|![Image](https://github.com/user-attachments/assets/e71b8c20-1629-41d9-b0ff-185805c1da4e)|![Image](https://github.com/user-attachments/assets/7a73c968-133a-4545-9aa2-205533861cd4)|![Image](https://github.com/user-attachments/assets/c8390b22-14fe-48a0-a6e6-d6556d31235e)| diff --git a/README_zh.md b/README_zh.md index 2ce2620..ce378a2 100644 --- a/README_zh.md +++ b/README_zh.md @@ -766,7 +766,7 @@ DiffSynth-Studio 不仅仅是一个工程化的模型框架,更是创新成果 - 论文:[Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation ](https://arxiv.org/abs/2602.03208) -- 代码样例:[]() +- 代码样例:coming soon |FLUX.1-dev|FLUX.1-dev + SES|Qwen-Image|Qwen-Image + SES| |-|-|-|-| @@ -774,6 +774,7 @@ DiffSynth-Studio 不仅仅是一个工程化的模型框架,更是创新成果 +
VIRAL:基于DiT模型的类比视觉上下文推理 @@ -789,6 +790,7 @@ DiffSynth-Studio 不仅仅是一个工程化的模型框架,更是创新成果
+
AttriCtrl: 图像生成模型的属性强度控制 diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-ICEdit.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-ICEdit.py new file mode 100644 index 0000000..8a90f6e --- /dev/null +++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-ICEdit.py @@ -0,0 +1,58 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import snapshot_download +from PIL import Image +import torch + +# Load models +vram_config = { + "offload_dtype": "disk", + "offload_device": "disk", + "onload_dtype": torch.float8_e4m3fn, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e4m3fn, + "preparing_device": "cuda", + "computation_dtype": torch.bfloat16, + "computation_device": "cuda", +} +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", **vram_config), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config), + ], + 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") \ No newline at end of file