7 6 5

谢集

sanaka87

https://horizonwind2004.github.io/

AI & ML interests

Image Generation

Recent Activity

new activity 4 days ago

RiverZ/ICEdit:Update app.py

new activity 5 days ago

RiverZ/ICEdit:Update README.md

posted an update 6 days ago

Our ICEdit's video is below~ 🔥 🔥🔥Huggingface DEMO: https://huggingface.co/spaces/RiverZ/ICEdit 🌐 Project Website: https://river-zhang.github.io/ICEdit-gh-pages/ 🏠 GitHub Repository: https://github.com/River-Zhang/ICEdit/blob/main/scripts/gradio_demo.py 🤗 Huggingface: https://huggingface.co/sanaka87/ICEdit-MoE-LoRA 📄 arxiv Paper: https://huggingface.co/papers/2504.20690

View all activity

Organizations

None yet

sanaka87's activity

New activity in RiverZ/ICEdit 4 days ago

Update app.py

#5 opened 4 days ago by

sanaka87

New activity in RiverZ/ICEdit 5 days ago

Update README.md

#4 opened 5 days ago by

sanaka87

posted an update 6 days ago

Post

2557

Our ICEdit's video is below~
🔥 🔥🔥Huggingface DEMO: RiverZ/ICEdit
🌐 Project Website: https://river-zhang.github.io/ICEdit-gh-pages/
🏠 GitHub Repository: https://github.com/River-Zhang/ICEdit/blob/main/scripts/gradio_demo.py
🤗 Huggingface: sanaka87/ICEdit-MoE-LoRA
📄 arxiv Paper: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

reacted to RiverZ's post with 🔥🤗 7 days ago

Post

2320

🚀 Excited to Share Our Latest Work: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer～

🎨 Daily Paper:
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔓 Code is now open source!
🔥 Huggingface DEMO:
RiverZ/ICEdit

🌐 Project Website: https://river-zhang.github.io/ICEdit-gh-pages/
🏠 GitHub Repository: https://github.com/River-Zhang/ICEdit/blob/main/scripts/gradio_demo.py
🤗 Huggingface:
sanaka87/ICEdit-MoE-LoRA

📄 arxiv Paper:
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔥 Why it’s cool:
- Achieves high-quality, multi-task image editing.
- Uses only 1% of the training parameters and 0.1% of the training data compared to existing methods — extremely efficient
- Beats several commercial models on background preservation, ID control, and consistency
- Open-source, low-cost, faster, and stronger — think of it as the “DeepSeek of image editing” 👀

We also implemented a Gradio demo app, available directly in our GitHub repo! And we made a flashy demo video — happy to send it your way!

replied to their post 7 days ago

updated a model 7 days ago

sanaka87/ICEdit-MoE-LoRA

Image-to-Image • Updated 7 days ago • 2.5k • 82

New activity in RiverZ/ICEdit 7 days ago

Update app.py

#2 opened 7 days ago by

sanaka87

authored a paper 7 days ago

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

Paper • 2504.20690 • Published 10 days ago • 18

New activity in RiverZ/ICEdit 8 days ago

Update app.py

#1 opened 8 days ago by

sanaka87

reacted to their post with 👍🔥 9 days ago

Post

2400

🚀 Excited to Share Our Latest Work: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer～

🎨 Daily Paper:
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔓 Code is now open source!
🔥 Huggingface DEMO: RiverZ/ICEdit
🌐 Project Website: https://river-zhang.github.io/ICEdit-gh-pages/
🏠 GitHub Repository: https://github.com/River-Zhang/ICEdit/blob/main/scripts/gradio_demo.py
🤗 Huggingface: sanaka87/ICEdit-MoE-LoRA
📄 arxiv Paper: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔥 Why it’s cool:
- Achieves high-quality, multi-task image editing.
- Uses only 1% of the training parameters and 0.1% of the training data compared to existing methods — extremely efficient
- Beats several commercial models on background preservation, ID control, and consistency
- Open-source, low-cost, faster, and stronger — think of it as the “DeepSeek of image editing” 👀

We also implemented a Gradio demo app, available directly in our GitHub repo! And we made a flashy demo video — happy to send it your way!

1 reply

posted an update 9 days ago

Post

2400

🚀 Excited to Share Our Latest Work: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer～

🎨 Daily Paper:
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔓 Code is now open source!
🔥 Huggingface DEMO: RiverZ/ICEdit
🌐 Project Website: https://river-zhang.github.io/ICEdit-gh-pages/
🏠 GitHub Repository: https://github.com/River-Zhang/ICEdit/blob/main/scripts/gradio_demo.py
🤗 Huggingface: sanaka87/ICEdit-MoE-LoRA
📄 arxiv Paper: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔥 Why it’s cool:
- Achieves high-quality, multi-task image editing.
- Uses only 1% of the training parameters and 0.1% of the training data compared to existing methods — extremely efficient
- Beats several commercial models on background preservation, ID control, and consistency
- Open-source, low-cost, faster, and stronger — think of it as the “DeepSeek of image editing” 👀

We also implemented a Gradio demo app, available directly in our GitHub repo! And we made a flashy demo video — happy to send it your way!