by XLabs-AI
Open source · 6k downloads · 542 likes
Flux ControlNet Collections offer a series of specialized ControlNet models designed specifically for Black Forest Labs' FLUX.1-dev model, enabling fine-grained control over image generation through precise visual constraints. The three available versions (Canny, HED, and Depth) provide guidance capabilities for edge detection, contour mapping, or depth perception, all optimized for 1024x1024 pixel resolution. These tools cater to artists, content creators, and developers seeking to refine their visual productions with structural or stylistic constraints. Their strength lies in seamless integration via ComfyUI, delivering an accessible user experience without requiring deep technical expertise. Released under a non-commercial license, these models stand out with their version 3, offering enhanced realism and performance ideal for professional-grade results.
This repository provides a collection of ControlNet checkpoints for FLUX.1-dev model by Black Forest Labs

See our github for comfy ui workflows.

See our github for train script, train configs and demo script for inference.
Our collection supports 3 models:
Each ControlNet is trained on 1024x1024 resolution and works for 1024x1024 resolution. We release v3 versions - better and realistic versions, which can be used directly in ComfyUI!
Please, see our ComfyUI custom nodes installation guide
See examples of our models results below.
Also, some generation results with input images are provided in "Files and versions"
To try our models, you have 2 options:
See examples how to launch our models:



Our weights fall under the FLUX.1 [dev] Non-Commercial License