ICEdit
ė¸ëļ ė ëŗ´
íėŧ ë¤ė´ëĄë (1)
ëĒ¨ë¸ ė¤ëĒ
đŽ Transform Your Images with Natural Language Instructions
Used with FluxFill-Dev The perfect companion for seamless editing
đ Overview: The Future of Image Editing is Here
ICEdit-MoE-LoRA represents a breakthrough in AI image editing - a lightweight Low-Rank Adaptation (LoRA) module that brings professional-grade, instruction-based editing capabilities to large diffusion transformers. By intelligently fine-tuning only 1% of parameters using just 0.5% of the original training data, it achieves extraordinary editing capabilities that match or even surpass premium commercial solutions.
đ ī¸ Complete Installation Guide
đ model Structure
đ ComfyUI/
âââ đ models/
â âââ đ text_encoders/
â â âââ đ clip_l.safetensors
â â âââ đ t5xxl_fp16.safetensors
â â âââ đ t5xxl_fp8_e4m3fn.safetensors
â â âââ đ t5xxl_fp8_e4m3fn_scaled.safetensors
â âââ đ vae/
â â âââ đ ae.safetensors
â âââ đ diffusion_models/
â â âââ đ fluxfill-dev.safetensors
â âââ đ lora/
â âââ đ [ICEdit-MoE.safetensorsđ Essential Components
đ¤ Text Encoders - The Brain Behind Natural Language Understanding
T5XXL Options - Choose based on your hardware capabilities:
đ VAE - The Visual Artist
đŧī¸ Diffusion Models - The Imaging Engine
⨠LoRA Models - The Magic Touch
đŦ Example Instructions You Can Try
"Add a majestic castle on the mountain in the background"
"Change the color of the car from red to electric blue"
"Remove the person from the image and replace with a flowering tree"
"Transform the style to watercolor painting while maintaining all details"
"Add dramatic sunset lighting to the scene"
đ Community Recognition
A special thank you to sanaka87 for revolutionizing open-source image editing by releasing the ICEdit-MoE-LoRA checkpoint and demos. Your contribution empowers creators everywhere and accelerates innovation across the AI art community!
My Node OLLAMAGEMINI
https://github.com/al-swaiti/ComfyUI-OllamaGemini

