From 57128dc89f8c8825c24eaa27000f1250a84b1ac3 Mon Sep 17 00:00:00 2001 From: mi804 <1576993271@qq.com> Date: Thu, 7 Aug 2025 13:42:47 +0800 Subject: [PATCH] update readme for qwen-image-eligen --- README.md | 2 +- README_zh.md | 2 +- examples/qwen_image/README.md | 2 +- examples/qwen_image/README_zh.md | 2 +- examples/qwen_image/model_inference/Qwen-Image-EliGen.py | 6 ------ 5 files changed, 4 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 7845523..181a645 100644 --- a/README.md +++ b/README.md @@ -363,7 +363,7 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## Update History -- **August 6, 2025** We open-sourced the entity control LoRA of Qwen-Image, [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen). Qwen-Image-EliGen is able to achieve entity-level controlled text-to-image generation. See the [paper](https://arxiv.org/abs/2501.01097) for technical details. Training dataset: [EliGenTrainSet](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet). +- **August 7, 2025** We open-sourced the entity control LoRA of Qwen-Image, [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen). Qwen-Image-EliGen is able to achieve entity-level controlled text-to-image generation. See the [paper](https://arxiv.org/abs/2501.01097) for technical details. Training dataset: [EliGenTrainSet](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet). - **August 5, 2025** We open-sourced the distilled acceleration model of Qwen-Image, [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full), achieving approximately 5x speedup. diff --git a/README_zh.md b/README_zh.md index 386cc3e..7007a0e 100644 --- a/README_zh.md +++ b/README_zh.md @@ -380,7 +380,7 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## 更新历史 -- **2025年8月6日** 我们开源了 Qwen-Image 的实体控制 LoRA 模型 [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)。Qwen-Image-EliGen 能够实现实体级受控的文本到图像生成。技术细节请参见[论文](https://arxiv.org/abs/2501.01097)。训练数据集：[EliGenTrainSet](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet)。 +- **2025年8月7日** 我们开源了 Qwen-Image 的实体控制 LoRA 模型 [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)。Qwen-Image-EliGen 能够实现实体级可控的文生图。技术细节请参见[论文](https://arxiv.org/abs/2501.01097)。训练数据集：[EliGenTrainSet](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet)。 - **2025年8月5日** 我们开源了 Qwen-Image 的蒸馏加速模型 [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)，实现了约 5 倍加速。 diff --git a/examples/qwen_image/README.md b/examples/qwen_image/README.md index eeb49c4..6eaa533 100644 --- a/examples/qwen_image/README.md +++ b/examples/qwen_image/README.md @@ -44,7 +44,7 @@ image.save("image.jpg") |-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image )|[code](./model_inference/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)| |[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_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-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_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.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_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)| ## Model Inference diff --git a/examples/qwen_image/README_zh.md b/examples/qwen_image/README_zh.md index 8e4563a..305e1ab 100644 --- a/examples/qwen_image/README_zh.md +++ b/examples/qwen_image/README_zh.md @@ -44,7 +44,7 @@ image.save("image.jpg") |-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./model_inference/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)| |[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_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-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_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.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_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)| ## 模型推理 diff --git a/examples/qwen_image/model_inference/Qwen-Image-EliGen.py b/examples/qwen_image/model_inference/Qwen-Image-EliGen.py index afee321..ab0fd14 100644 --- a/examples/qwen_image/model_inference/Qwen-Image-EliGen.py +++ b/examples/qwen_image/model_inference/Qwen-Image-EliGen.py @@ -121,12 +121,6 @@ global_prompt = "A captivating, dramatic scene in a painting that exudes mystery entity_prompts = ["crescent yellow moon", "a solitary woman", "water", "swirling blue clouds"] example(pipe, [0], 5, global_prompt, entity_prompts) -# example 6, poster -seeds = range(0, 1) -global_prompt = "瑞幸咖啡蓝莓奶背的宣传海报，主体是两杯浅绿色的瑞幸蓝莓奶昔杯装饮品，背景是浅蓝色水雾，海报写着“Luckin Coffee 蓝莓奶昔闪耀回归”，“新品上市” " -entity_prompts = ["杯装饮品", "杯装饮品", "字：“新品上市”", "字：“Luckin Coffee 蓝莓奶昔闪耀回归”"] -example(pipe, seeds, 6, global_prompt, entity_prompts) - # example 7, same prompt with different seeds seeds = range(5, 9) global_prompt = "A beautiful asia woman wearing white dress, holding a mirror, with a forest background."