Update README.md

README.md

@@ -1,4 +1,179 @@
----
-license: apache-2.0
-library_name: diffusers
----
+---
+license: apache-2.0
+library_name: diffusers
+datasets:
+- VisualCloze/Graph200K
+base_model:
+- black-forest-labs/FLUX.1-Fill-dev
+pipeline_tag: image-to-image
+tags:
+- text-to-image
+- image-to-image
+- flux
+- lora
+- in-context-learning
+- universal-image-generation
+- ai-tools
+---
+
+
+# VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning (Implementation with <strong><span style="color:red">Diffusers</span></strong>)
+
+<div align="center">
+
+[[Paper](https://arxiv.org/abs/2504.07960)] &emsp; [[Project Page](https://visualcloze.github.io/)] &emsp; [[Github](https://github.com/lzyhha/VisualCloze)] &emsp;
+
+</div>
+
+<div align="center">
+
+[[🤗 <strong><span style="color:hotpink">Diffusers</span></strong> Implementation](https://github.com/lzyhha/diffusers)]
+
+</div>
+
+<div align="center">
+
+[[🤗 Online Demo](https://huggingface.co/spaces/VisualCloze/VisualCloze)] &emsp; [[🤗 Dataset Card](https://huggingface.co/datasets/VisualCloze/Graph200K)]
+
+</div>
+
+
+## 🌠 Key Features:
+
+An in-context learning based universal image generation framework. 
+
+1. Support various in-domain tasks.
+2. Generalize to <strong><span style="color:hotpink"> unseen tasks</span></strong> through in-context learning. 
+3. Unify multiple tasks into one step and generate both target image and intermediate results. 
+4. Support reverse-engineering a set of conditions from a target image.
+
+🔥 Examples are shown in the [project page](https://visualcloze.github.io/).
+
+## 🔧 Installation
+
+Install diffusers from our modified repository.
+```bash
+git clone https://github.com/lzyhha/diffusers
+
+cd diffusers
+pip install -v -e .
+```
+
+### 💻 Diffusers Usage
+
+[![Huggingface VisualCloze](https://img.shields.io/static/v1?label=Demo&message=Huggingface%20Gradio&color=orange)](https://huggingface.co/spaces/VisualCloze/VisualCloze)
+
+Example with Depth-to-Image:
+```python
+import torch
+from diffusers import VisualClozePipeline
+from diffusers.utils import load_image
+from PIL import Image
+
+# Load in-context images (make sure the paths are correct and accessible)
+image_paths = [
+    # in-context examples
+    [
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/5bf755ed9dbb9b3e223e7ba35232b06e/5bf755ed9dbb9b3e223e7ba35232b06e_depth-anything-v2_Large.jpg'),
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/5bf755ed9dbb9b3e223e7ba35232b06e/5bf755ed9dbb9b3e223e7ba35232b06e.jpg'),
+    ],
+    # query with the target image
+    [
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/2b74476568f7562a6aa832d423132ed3/2b74476568f7562a6aa832d423132ed3_depth-anything-v2_Large.jpg'),
+        None,  # No image needed for the query in this case
+    ],
+]
+
+# Task and content prompt
+task_prompt = "Each row outlines a logical process, starting from [IMAGE1] gray-based depth map with detailed object contours, to achieve [IMAGE2] an image with flawless clarity."
+content_prompt = """Group photo of five young adults enjoying a rooftop gathering at dusk. The group is positioned in the center, with three women and two men smiling and embracing. 
+The woman on the far left wears a floral top and holds a drink, looking slightly to the right. 
+Next to her, a woman in a denim jacket stands close to a woman in a white blouse, both smiling directly at the camera. 
+The fourth woman, in an orange top, stands close to the man on the far right, who wears a red shirt and blue blazer, smiling broadly. 
+The background features a cityscape with a tall building and string lights hanging overhead, creating a warm, festive atmosphere. 
+Soft natural lighting, warm color palette, shallow depth of field, intimate and joyful mood, slightly blurred background, urban rooftop setting, evening ambiance."""
+
+# Load the VisualClozePipeline
+pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()  # Save some VRAM by offloading the model to CPU
+
+# Run the pipeline
+image_result = pipe(
+    task_prompt=task_prompt,
+    content_prompt=content_prompt,
+    image=image_paths,
+    height=1632,
+    width=1232,
+    upsampling_strength=0.4,
+    guidance_scale=30,
+    num_inference_steps=50,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0]
+
+# Save the resulting image
+image_result.save("visualcloze.png")
+```
+
+
+Example with Virtual Try-On:
+```python
+import torch
+from diffusers import VisualClozePipeline
+from diffusers.utils import load_image
+from PIL import Image
+
+# Load in-context images (make sure the paths are correct and accessible)
+image_paths = [
+    # in-context examples
+    [
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/tryon/00700_00.jpg'),
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/tryon/03673_00.jpg'),
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/tryon/00700_00_tryon_catvton_0.jpg'),
+    ],
+    # query with the target image
+    [
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/tryon/00555_00.jpg'),
+        load_image('https://github.com/lzyhha/VisualCloze/tree/main/examples/examples/tryon/12265_00.jpg'),
+        None
+    ],
+]
+
+# Task and content prompt
+task_prompt = "Each row shows a virtual try-on process that aims to put [IMAGE2] the clothing onto [IMAGE1] the person, producing [IMAGE3] the person wearing the new clothing."
+content_prompt = None
+
+# Load the VisualClozePipeline
+pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()  # Save some VRAM by offloading the model to CPU
+
+# Run the pipeline
+image_result = pipe(
+    task_prompt=task_prompt,
+    content_prompt=content_prompt,
+    image=image_paths,
+    height=1632,
+    width=1232,
+    upsampling_strength=0.4,
+    guidance_scale=30,
+    num_inference_steps=50,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0]
+
+# Save the resulting image
+image_result.save("visualcloze.png")
+```
+
+### Citation
+
+If you find VisualCloze useful for your research and applications, please cite using this BibTeX:
+
+```bibtex
+@article{li2025visualcloze,
+  title={VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning},
+  author={Li, Zhong-Yu and Du, Ruoyi and Yan, Juncheng and Zhuo, Le and Li, Zhen and Gao, Peng and Ma, Zhanyu and Cheng, Ming-Ming},
+  journal={arXiv preprint arXiv:2504.07960},
+  year={2025}
+}
+```