Sign In
homemodelsimagesvideospostsarticlesbountieschallengeseventsupdatesshop

FLUX.Fill-dev(gguf)

86

2.6k

33

Updated: May 17, 2025

base model

Download (7.85 GB)

Verified:

GGUF

Type

Checkpoint Trained

Stats

1,621

0

Reviews

(61)

Published

Jan 7, 2025

Base Model

Flux.1 D Inpainting

Hash

AutoV2
2829D9DF5E
default creator card background decoration
SDXL Image Contest Participant
AbdallahAlswa80's Avatar

AbdallahAlswa80

License:

FLUX.1 [dev] Non-Commercial License

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

🌊 FLUX.1-Fill-dev Quantized: Advanced Diffusion for Seamless Image Editing

📌 Overview

FLUX.1-Fill-dev Quantized represents a breakthrough in efficient diffusion models for image editing. Built on Black Forest Labs' original architecture and optimized through GGUF quantization, it delivers professional-grade inpainting and outpainting capabilities while maintaining impressive performance even on consumer hardware.

🔑 Key Features

  • Optimized Performance: Multiple quantization options (Q8, Q5_K_M, Q4_K_M) to balance quality and speed

  • Versatile Editing: Excels at both inpainting (filling missing areas) and outpainting (extending images beyond boundaries)

  • Seamless Integration: Compatible with popular frameworks like ComfyUI and other diffusion workflows

  • Memory Efficient: Reduced model size without significant quality degradation

⚡ Available Versions

  • Q8 Quantization: Highest quality, larger model size (recommended for high-end GPUs)

  • Q5_K_M Quantization: Balanced performance and quality

  • Q4_K_M Quantization: Fastest performance, smallest size (ideal for lower-end hardware)

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── 📄 fluxfill-dev-q8.gguf (or q5km or q4km)
│   ├── 📂 text_encoders/
│   │   ├── 📄 clip_l.safetensors
│   │   └── 📄 t5xxl_fp8_e4m3fn.safetensors (fp16 or fp8 scaled)
│   ├── 📂 vae/
│   │   └── 📄 ae.safetensors

🚀 Getting Started

System Requirements

  • Minimum: 8GB VRAM (with Q4_K_M)

  • Recommended: 12GB+ VRAM (for Q8 version)

  • Optimal: 16GB+ VRAM (for complex workflows)

Installation Steps

  1. Download your preferred quantization version

  2. Place the model file in your ComfyUI/models/diffusion_models/ directory

  3. Download required text encoders from Hugging Face

  4. Download the VAE from Hugging Face

Note: You only need to choose ONE of the T5XXL options below based on your hardware capabilities

💎 Optimal Workflows

  • 🎨 Professional Inpainting

    • FLUX.1-Fill-dev excels at seamlessly patching areas within images while maintaining perfect context awareness:

      1. Load your image into ComfyUI

      2. Create or upload a mask for the area to fill

      3. Use 20-30 steps with a sampling method like DPM++ 2M Karras

  • 🏞️ Creative Outpainting

    • Extend your images beyond their original boundaries with natural continuity:

      1. Load your image into ComfyUI

      2. Use the FluxFill outpainting workflow

      3. Choose the direction(s) to extend the image

🙏 Credits

  • Special thanks to Black Forest Labs for developing the original FLUX.1-Fill-dev model.

👨‍💻 Developer Information

This workflow guide was created by Abdallah Al-Swaiti:

For additional tools and updates, check out the OllamaGemini Node: GitHub Repository

✨ Elevate Your Creative Vision ✨

No alternative text description for this image