lxa9867/ControlVAR
This is the official implementation for ControlVAR.
This project helps researchers and developers explore and implement advanced visual autoregressive modeling. It takes an original ImageNet dataset alongside various controlled conditions like masks, canny edges, depth maps, and normal maps, and uses them to generate new images based on these specific controls. The primary users are researchers and engineers working on controllable image generation.
126 stars. No commits in the last 6 months.
Use this if you are a researcher or engineer looking to train and evaluate models for highly controllable image generation from diverse inputs like masks, edges, and depth information.
Not ideal if you need a simple, out-of-the-box solution for basic image generation without complex conditional controls, or if you're not comfortable with Python development.
Stars
126
Forks
7
Language
Python
License
—
Category
Last pushed
Dec 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lxa9867/ControlVAR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...