360CVGroup/RelaCtrl
Efficient controlnet for DiTs
This project helps AI developers and researchers generate highly specific images from text prompts by giving them fine-grained control over the output. You provide a text description and an additional condition, like an edge map (Canny) or a style reference, and it produces an image that adheres to both inputs. This is ideal for those creating new visual content and requiring precise artistic or structural guidance.
383 stars. No commits in the last 6 months.
Use this if you need to generate images from text while also controlling specific visual aspects like outlines or artistic styles with greater efficiency.
Not ideal if you just need basic image generation from text without specific control over structural or stylistic elements.
Stars
383
Forks
35
Language
Python
License
—
Category
Last pushed
May 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/360CVGroup/RelaCtrl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hnsywangxin/controlnet_stable_tensorrt
stable diffusion, controlnet, tensorrt, accelerate
a-lgil/pose-depot
A collection of ControlNet poses
city96/SD-Latent-Upscaler
Upscaling stable diffusion latents using a small neural network.
camenduru/ControlNet-v1-1-nightly-colab
controlnet v1.1 colab
Haoming02/FIRST
Frame Interpolation Refined with Stable Diffusion via Control Net