open-mmlab/AnyControl
[ECCV 2024] AnyControl, a multi-control image synthesis model that supports any combination of user provided control signals. 一个支持用户自由输入控制信号的图像生成模型，能够根据多种控制生成自然和谐的结果！
This tool helps graphic designers, artists, and marketers create custom images by combining multiple visual instructions. You provide a text description and various control signals like outlines, depth maps, or body poses, and it generates a coherent, high-quality image that incorporates all your specified elements. It's designed for anyone needing precise artistic control over AI image generation.
130 stars. No commits in the last 6 months.
Use this if you need to generate images from text but also want fine-grained control over specific visual aspects, such as object shapes, spatial arrangement, or human poses.
Not ideal if you only need basic image generation from a text prompt without additional visual constraints, or if you require real-time image creation for live applications.
Stars
130
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jul 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/open-mmlab/AnyControl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lixinustc/Awesome-diffusion-model-for-image-processing
one summary of diffusion-based image processing, including restoration, enhancement, coding,...
showlab/Awesome-Video-Diffusion
A curated list of recent diffusion models for video generation, editing, and various other applications.
xlite-dev/Awesome-DiT-Inference
📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization,...
wangkai930418/awesome-diffusion-categorized
collection of diffusion model papers categorized by their subareas
ChenHsing/Awesome-Video-Diffusion-Models
[CSUR] A Survey on Video Diffusion Models