upload

.gitattributes

@@ -33,3 +33,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/style/1/image_2.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/2/0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/2/1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/2/2.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/2/3.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/2/4.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/2/5.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/3/image_0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/3/image_1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/2.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/3.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/4.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/5.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/image_0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/image_1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/4/image_2.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/5/2.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/5/image_0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/style/5/image_2.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,185 @@
----
-license: apache-2.0
----
+---
+
+frameworks:
+- Pytorch
+license: apache-2.0
+tags: []
+tasks:
+- text-to-image-synthesis
+base_model:
+  - Tongyi-MAI/Z-Image
+base_model_relation: adapter
+---
+## 模型介绍
+
+i2L (Image to LoRA) 模型是我们以疯狂的思路设计的模型结构。模型的输入为一张图片，输出为这张图片训练出的 LoRA 模型。本模型基于我们之前的 Qwen-Image-i2L（[模型](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-i2L)、[技术博客](https://modelscope.cn/learn/3343)），进一步完善并迁移到 [Z-Image](https://modelscope.cn/models/Tongyi-MAI/Z-Image)，着重增强了模型的风格保持能力。
+
+为保证生成的图像质量，我们建议按以下参数使用本模型产生的 LoRA 模型：
+
+* 使用负向提示词
+    * 中文：`"泛黄，发绿，模糊，低分辨率，低质量图像，扭曲的肢体，诡异的外观，丑陋，AI感，噪点，网格感，JPEG压缩条纹，异常的肢体，水印，乱码，意义不明的字符"`
+    * 英文：`"Yellowed, green-tinted, blurry, low-resolution, low-quality image, distorted limbs, eerie appearance, ugly, AI-looking, noise, grid-like artifacts, JPEG compression artifacts, abnormal limbs, watermark, garbled text, meaningless characters"`
+* `cfg_scale = 4`
+* `sigma_shift = 8`
+* 仅在正向提示词侧启用 LoRA，在负向提示词侧关闭 LoRA，这会提升图像质量
+
+在线体验：https://modelscope.cn/studios/DiffSynth-Studio/Z-Image-i2L
+
+## 效果展示
+
+Z-Image-i2L 模型可用于快速生成风格 LoRA，只需输入几张风格统一的图像。以下是我们生成的结果，随机种子都是 0。
+
+### 风格1：水彩绘画
+
+输入图像：
+
+|![](./assets/style/1/0.jpg)|![](./assets/style/1/1.jpg)|![](./assets/style/1/2.jpg)|![](./assets/style/1/3.jpg)|
+|-|-|-|-|
+
+生成图像：
+
+|a cat|a dog|a girl|
+|-|-|-|
+|![](./assets/style/1/image_0.jpg)|![](./assets/style/1/image_1.jpg)|![](./assets/style/1/image_2.jpg)|
+
+### 风格2：写实细节
+
+输入图像：
+
+|![](./assets/style/5/0.jpg)|![](./assets/style/5/1.jpg)|![](./assets/style/5/2.jpg)|![](./assets/style/5/3.jpg)|![](./assets/style/5/4.jpg)|
+|-|-|-|-|-|
+
+生成图像：
+
+|a cat|a dog|a girl|
+|-|-|-|
+|![](./assets/style/5/image_0.jpg)|![](./assets/style/5/image_1.jpg)|![](./assets/style/5/image_2.jpg)|
+
+### 风格3：缤纷色块
+
+输入图像：
+
+|![](./assets/style/2/0.jpg)|![](./assets/style/2/1.jpg)|![](./assets/style/2/2.jpg)|![](./assets/style/2/3.jpg)|![](./assets/style/2/4.jpg)|![](./assets/style/2/5.jpg)|
+|-|-|-|-|-|-|
+
+生成图像：
+
+|a cat|a dog|a girl|
+|-|-|-|
+|![](./assets/style/2/image_0.jpg)|![](./assets/style/2/image_1.jpg)|![](./assets/style/2/image_2.jpg)|
+
+### 风格4：鲜花少女
+
+输入图像：
+
+|![](./assets/style/3/0.jpg)|![](./assets/style/3/1.jpg)|![](./assets/style/3/2.jpg)|![](./assets/style/3/3.jpg)|
+|-|-|-|-|
+
+生成图像：
+
+|a cat|a dog|a girl|
+|-|-|-|
+|![](./assets/style/3/image_0.jpg)|![](./assets/style/3/image_1.jpg)|![](./assets/style/3/image_2.jpg)|
+
+### 风格5：黑白简约
+
+输入图像：
+
+|![](./assets/style/6/0.jpg)|![](./assets/style/6/1.jpg)|![](./assets/style/6/2.jpg)|![](./assets/style/6/3.jpg)|
+|-|-|-|-|
+
+生成图像：
+
+|a cat|a dog|a girl|
+|-|-|-|
+|![](./assets/style/6/image_0.jpg)|![](./assets/style/6/image_1.jpg)|![](./assets/style/6/image_2.jpg)|
+
+### 风格6：幻想世界
+
+输入图像：
+
+|![](./assets/style/4/0.jpg)|![](./assets/style/4/1.jpg)|![](./assets/style/4/2.jpg)|![](./assets/style/4/3.jpg)|![](./assets/style/4/4.jpg)|![](./assets/style/4/5.jpg)|
+|-|-|-|-|-|-|
+
+生成图像：
+
+|a cat|a dog|a girl|
+|-|-|-|
+|![](./assets/style/4/image_0.jpg)|![](./assets/style/4/image_1.jpg)|![](./assets/style/4/image_2.jpg)|
+
+## 推理代码
+
+安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)：
+
+```shell
+git clone https://github.com/modelscope/DiffSynth-Studio.git  
+cd DiffSynth-Studio
+pip install -e .
+```
+
+模型推理：
+
+```python
+from diffsynth.pipelines.z_image import (
+    ZImagePipeline, ModelConfig,
+    ZImageUnit_Image2LoRAEncode, ZImageUnit_Image2LoRADecode
+)
+from modelscope import snapshot_download
+from safetensors.torch import save_file
+import torch
+from PIL import Image
+
+# Use `vram_config` to enable LoRA hot-loading
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cuda",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+
+# Load models
+pipe = ZImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="transformer/*.safetensors", **vram_config),
+        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"),
+        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="SigLIP2-G384/model.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="DINOv3-7B/model.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/Z-Image-i2L", origin_file_pattern="model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
+)
+
+# Load images
+snapshot_download(
+    model_id="DiffSynth-Studio/Z-Image-i2L",
+    allow_file_pattern="assets/style/*",
+    local_dir="data/Z-Image-i2L_style_input"
+)
+images = [Image.open(f"data/Z-Image-i2L_style_input/assets/style/1/{i}.jpg") for i in range(4)]
+
+# Image to LoRA
+with torch.no_grad():
+    embs = ZImageUnit_Image2LoRAEncode().process(pipe, image2lora_images=images)
+    lora = ZImageUnit_Image2LoRADecode().process(pipe, **embs)["lora"]
+save_file(lora, "lora.safetensors")
+
+# Generate images
+prompt = "a cat"
+negative_prompt = "泛黄，发绿，模糊，低分辨率，低质量图像，扭曲的肢体，诡异的外观，丑陋，AI感，噪点，网格感，JPEG压缩条纹，异常的肢体，水印，乱码，意义不明的字符"
+image = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    positive_only_lora=lora,
+    sigma_shift=8
+)
+image.save("image.jpg")
+```
+

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-to-image-synthesis"}