From b08bc1470d5288710bf86d06aa9fb20ac7add074 Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Sun, 15 Feb 2026 14:02:50 +0800 Subject: [PATCH] support firered --- README.md | 1 + README_zh.md | 1 + docs/en/Model_Details/Qwen-Image.md | 1 + docs/zh/Model_Details/Qwen-Image.md | 1 + .../model_inference/FireRed-Image-Edit-1.0.py | 43 +++++++++++++++ .../FireRed-Image-Edit-1.0.py | 54 +++++++++++++++++++ .../full/FireRed-Image-Edit-1.0.sh | 15 ++++++ .../lora/FireRed-Image-Edit-1.0.sh | 18 +++++++ .../validate_full/FireRed-Image-Edit-1.0.py | 26 +++++++++ .../validate_lora/FireRed-Image-Edit-1.0.py | 24 +++++++++ 10 files changed, 184 insertions(+) create mode 100644 examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py create mode 100644 examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py create mode 100644 examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh create mode 100644 examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh create mode 100644 examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py create mode 100644 examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py diff --git a/README.md b/README.md index d7d3752..9bbcb85 100644 --- a/README.md +++ b/README.md @@ -419,6 +419,7 @@ Example code for Qwen-Image is available at: [/examples/qwen_image/](/examples/q |[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)| |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| +|[FireRedTeam/FireRed-Image-Edit-1.0](https://www.modelscope.cn/models/FireRedTeam/FireRed-Image-Edit-1.0)|[code](/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py)| |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| diff --git a/README_zh.md b/README_zh.md index ce378a2..5fce400 100644 --- a/README_zh.md +++ b/README_zh.md @@ -419,6 +419,7 @@ Qwen-Image 的示例代码位于：[/examples/qwen_image/](/examples/qwen_image/ |[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)| |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| +|[FireRedTeam/FireRed-Image-Edit-1.0](https://www.modelscope.cn/models/FireRedTeam/FireRed-Image-Edit-1.0)|[code](/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py)| |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| diff --git a/docs/en/Model_Details/Qwen-Image.md b/docs/en/Model_Details/Qwen-Image.md index 0c55a94..fddd096 100644 --- a/docs/en/Model_Details/Qwen-Image.md +++ b/docs/en/Model_Details/Qwen-Image.md @@ -85,6 +85,7 @@ graph LR; | [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) | | [Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509) | [code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh) | [code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh) | [code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py) | |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| +|[FireRedTeam/FireRed-Image-Edit-1.0](https://www.modelscope.cn/models/FireRedTeam/FireRed-Image-Edit-1.0)|[code](/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py)| |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| diff --git a/docs/zh/Model_Details/Qwen-Image.md b/docs/zh/Model_Details/Qwen-Image.md index 566765c..745d7a3 100644 --- a/docs/zh/Model_Details/Qwen-Image.md +++ b/docs/zh/Model_Details/Qwen-Image.md @@ -85,6 +85,7 @@ graph LR; |[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)| |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| +|[FireRedTeam/FireRed-Image-Edit-1.0](https://www.modelscope.cn/models/FireRedTeam/FireRed-Image-Edit-1.0)|[code](/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py)|[code](/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh)|[code](/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py)| |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| diff --git a/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py b/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py new file mode 100644 index 0000000..10008e0 --- /dev/null +++ b/examples/qwen_image/model_inference/FireRed-Image-Edit-1.0.py @@ -0,0 +1,43 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import dataset_snapshot_download +from PIL import Image +import torch + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="FireRedTeam/FireRed-Image-Edit-1.0", 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"), + ], + processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"), +) + +dataset_snapshot_download( + "DiffSynth-Studio/example_image_dataset", + allow_file_pattern="qwen_image_edit/*", + local_dir="data/example_image_dataset", +) + +prompt = "生成这两个人的合影" +edit_image = [ + Image.open("data/example_image_dataset/qwen_image_edit/image1.jpg"), + Image.open("data/example_image_dataset/qwen_image_edit/image2.jpg"), +] +image = pipe( + prompt, + edit_image=edit_image, + seed=1, + num_inference_steps=40, + height=1152, + width=896, + edit_image_auto_resize=True, +) +image.save("image.jpg") + +# FireRedTeam/FireRed-Image-Edit-1.0 is a multi-image editing model. +# Please use a list to input `edit_image`, even if the input contains only one image. +# edit_image = [Image.open("image.jpg")] +# Please do not input the image directly. +# edit_image = Image.open("image.jpg") diff --git a/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py b/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py new file mode 100644 index 0000000..8112166 --- /dev/null +++ b/examples/qwen_image/model_inference_low_vram/FireRed-Image-Edit-1.0.py @@ -0,0 +1,54 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import dataset_snapshot_download +from PIL import Image +import torch + +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="FireRedTeam/FireRed-Image-Edit-1.0", 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/"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) + +dataset_snapshot_download( + "DiffSynth-Studio/example_image_dataset", + allow_file_pattern="qwen_image_edit/*", + local_dir="data/example_image_dataset", +) + +prompt = "生成这两个人的合影" +edit_image = [ + Image.open("data/example_image_dataset/qwen_image_edit/image1.jpg"), + Image.open("data/example_image_dataset/qwen_image_edit/image2.jpg"), +] +image = pipe( + prompt, + edit_image=edit_image, + seed=1, + num_inference_steps=40, + height=1152, + width=896, + edit_image_auto_resize=True, +) +image.save("image.jpg") + +# FireRedTeam/FireRed-Image-Edit-1.0 is a multi-image editing model. +# Please use a list to input `edit_image`, even if the input contains only one image. +# edit_image = [Image.open("image.jpg")] +# Please do not input the image directly. +# edit_image = Image.open("image.jpg") diff --git a/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh b/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh new file mode 100644 index 0000000..2f1b458 --- /dev/null +++ b/examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh @@ -0,0 +1,15 @@ +accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \ + --dataset_base_path data/example_image_dataset \ + --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \ + --data_file_keys "image,edit_image" \ + --extra_inputs "edit_image" \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "FireRedTeam/FireRed-Image-Edit-1.0:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \ + --learning_rate 1e-5 \ + --num_epochs 2 \ + --remove_prefix_in_ckpt "pipe.dit." \ + --output_path "./models/train/FireRed-Image-Edit-1.0_full" \ + --trainable_models "dit" \ + --use_gradient_checkpointing \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh b/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh new file mode 100644 index 0000000..6d7aaff --- /dev/null +++ b/examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh @@ -0,0 +1,18 @@ +accelerate launch examples/qwen_image/model_training/train.py \ + --dataset_base_path data/example_image_dataset \ + --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \ + --data_file_keys "image,edit_image" \ + --extra_inputs "edit_image" \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "FireRedTeam/FireRed-Image-Edit-1.0: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/FireRed-Image-Edit-1.0_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 32 \ + --use_gradient_checkpointing \ + --dataset_num_workers 8 \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py b/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py new file mode 100644 index 0000000..3c0d07b --- /dev/null +++ b/examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py @@ -0,0 +1,26 @@ +import torch +from PIL import Image +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from diffsynth import load_state_dict + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="FireRedTeam/FireRed-Image-Edit-1.0", 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/"), +) +state_dict = load_state_dict("models/train/FireRed-Image-Edit-1.0_full/epoch-1.safetensors") +pipe.dit.load_state_dict(state_dict) + +prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2." +images = [ + Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)), + Image.open("data/example_image_dataset/edit/image_color.jpg").resize((1024, 1024)), +] +image = pipe(prompt, edit_image=images, seed=123, num_inference_steps=40, height=1024, width=1024) +image.save("image.jpg") diff --git a/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py b/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py new file mode 100644 index 0000000..b5b0046 --- /dev/null +++ b/examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py @@ -0,0 +1,24 @@ +import torch +from PIL import Image +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="FireRedTeam/FireRed-Image-Edit-1.0", 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/"), +) +pipe.load_lora(pipe.dit, "models/train/FireRed-Image-Edit-1.0_lora/epoch-4.safetensors") + +prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2." +images = [ + Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)), + Image.open("data/example_image_dataset/edit/image_color.jpg").resize((1024, 1024)), +] +image = pipe(prompt, edit_image=images, seed=123, num_inference_steps=40, height=1024, width=1024) +image.save("image.jpg")