Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
🔮 Transform Your Images with Natural Language Instructions
Runtime profile
Source description
🔮 Transform Your Images with Natural Language Instructions
The Perfect Companion for Seamless Editing
This guide outlines a complete workflow using FluxFill-Dev with ICEdit-MoE-LoRA for powerful natural language-based image editing.
📝 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.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
ICEdit-workflow is for editing an input image with natural-language instructions; it can add, remove, replace, recolor, restyle, or relight image content, using the image and an edit instruction to produce a preview and a saved image.
The workflow combines FluxFill-Dev with ICEdit-MoE-LoRA for instruction-based image editing.
It includes image loading, inpainting conditioning, sampling, preview, saving, scaling, and model-based upscaling stages.
The workflow lists a Gemini auto-prompt node and the LEOPARD, Bernoulli, and SPEED_Q8 model options.
Use an input image with an instruction such as adding a castle, changing a car’s color, replacing a person with a tree, applying watercolor style, or adding sunset lighting.
The setup guide places model files in ComfyUI folders named diffusion_models, text_encoders, vae, and lora.
The listed model files are ae.safetensors, clip_l_hidream.safetensors, flux1-dev.safetensors, ICEdit-MoE-LoRA.safetensors, and t5xxl_fp8_e4m3fn_scaled.safetensors.
The list also includes q5km-fill.gguf, q6_K.gguf, general/4x-UltraSharp.pth, and RealESRGAN_x4plus.pth.
The listed node packs are ComfyUI_Comfyroll_CustomNodes, comfyui_essentials, comfyui-custom-scripts, comfyui-easy-use, ComfyUI-GGUF, comfyui-ollamagemini, rgthree-comfy, and wavespeed.
The guide says to choose one T5XXL text encoder: t5xxl_fp16.safetensors, t5xxl_fp8_e4m3fn.safetensors, or t5xxl_fp8_e4m3fn_scaled.safetensors.
It lists fluxfill-dev.safetensors as the core editing model, with LEOPARD.gguf, Bernoulli.gguf, and SPEED_Q8.gguf as alternatives.
Before setup, verify the availability and exact filenames of clip_l_hidream.safetensors, ICEdit-MoE-LoRA.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors, q5km-fill.gguf, and q6_K.gguf.
Suggestion · not verified
Before setup, verify that ComfyUI-GGUF and wavespeed are available under those exact names.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
2 excerptsSource context: 1192 downloads · Type Workflows · Base model Flux.1 D
📌 Complete Workflow
This workflow combines FluxFill + ICEdit-MoE-LoRA for editing images with natural language instructions. For enhanced results, diffusion models like LEOPARD , Bernoulli or SPEED_Q8 with the Gemini auto prompt node in 4-8 steps.(i used very light flux model which need less steps)
A diptych with two side-by-side images of the same scene. On the right, the scene is the same as on the left but "your edit"( prostyle included just put ur edit )
🛠️ Complete Installation Guide
📁 Setup Structure
📂 ComfyUI/ ├── 📂 models/ │ ├── 📂 diffusion_models/ │ │ ├── (basic)📄 fluxfill-dev.safetensors # https://civitai.com/models/1108146/fluxfill-devgguf │ │ ├──(option1)📄 LEOPARD.gguf # https://civitai.com/models/1534861 │ │ ├──(option2)📄 Bernoulli.gguf # https://civitai.com/models/682369 │ │ └──(option3)📄 SPEED_Q8.gguf # https://civitai.com/models/661102/speedq8 │ ├── 📂 text_encoders/ │ │ ├── (basic)📄 clip_l.safetensors │ │ ├── (option1)📄 t5xxl_fp16.safetensors │ │ ├── (option2)📄 t5xxl_fp8_e4m3fn.safetensors │ │ └── (option3)📄 t5xxl_fp8_e4m3fn_scaled.safetensors │ ├── 📂 vae/ │ │ └── 📄 ae.safetensors │ └── 📂 lora/ │ └── 📄 ICEdit-MoE.safetensors
💎 Essential Components
✨ LoRA Models - The Magic Touch
ICEdit-MoE.safetensors - The star of the show!
🔤 Text Encoders - The Brain Behind Natural Language Understanding
Note: You only need to choose ONE of the T5XXL options below based on your hardware capabilities
clip_l.safetensors - Core understanding model
T5XXL Options (choose only one):
t5xxl_fp16.safetensors - Highest quality, more demanding
t5xxl_fp8_e4m3fn.safetensors - Balanced performance
t5xxl_fp8_e4m3fn_scaled.safetensors - Optimized for speed
🎭 VAE - The Visual Artist
ae.safetensors - Included in the FluxFill package
🖼️ Diffusion Models - The Imaging Engine
fluxfill-dev.safetensors - Core diffusion model for editing
##(You only need to choose ONE of those or use flux-dev itself its up to u)
LEOPARD.safetensors - Advanced diffusion model for refined outputs
Bernoulli.safetensors - Alternative diffusion model for enhanced generation
SPEED_Q8.gguf - Enhanced flux-dev model for improved results
Note: Any of these diffusion models can be used for efficient editing with fewer steps (4-8 steps recommended). Use flux-dev-fill for editing and flux-dev for enhancing results.
🎬 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"
👨💻 Developer Information
This workflow guide was created by Abdallah Al-Swaiti:
LinkedIn Profile
GitHub
Hugging Face
For additional tools and updates, check out the OllamaGemini Node: GitHub Repository
🙏 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!
Estimated VRAM requirement
Estimate unavailable
22.3 GB across 3 of 9 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
17 requirementsVAE · Unknown
clip_l_hidream.safetensors
ConflictText encoder · Unknown
Checkpoint · 22.2 GB · SAFETENSORS · fp32 · full · Unknown
Upscaler · 63.9 MB · PT · Hugging Face · general/4x-UltraSharp.pth
ICEdit-MoE-LoRA.safetensors
Not resolvedLoRA · Unknown
q5km-fill.gguf
Not resolvedCheckpoint · Unknown
q6_K.gguf
Not resolvedCheckpoint · Unknown
Upscaler · 63.9 MB · PT · GitHub · xinntao/Real-ESRGAN
t5xxl_fp8_e4m3fn_scaled.safetensors
ConflictText encoder · Unknown
Node pack · Registry
Node pack · Registry
Source context: 1191 downloads · Type Workflows · Base model Flux.1 D
Node pack · Registry
Node pack · Registry
ComfyUI-GGUF
PossibleNode pack · Registry
Node pack · Registry
Node pack · Registry
wavespeed
Not resolvedNode pack · Registry
