energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
[ECCV 2022] Compositional Generation using Diffusion Models
This project helps graphic designers, artists, and 3D modelers create more precise and complex images and 3D objects using AI text-to-image models like Stable Diffusion or Point-E. You input multiple descriptive text prompts, and it generates an image or 3D mesh that combines or excludes elements based on your instructions. The result is a highly customized visual output that closely matches your creative vision.
485 stars. No commits in the last 6 months.
Use this if you need to generate images or 3D models with specific combinations of features or if you want to explicitly exclude certain elements using natural language prompts.
Not ideal if you prefer to generate visuals with a single, straightforward text prompt without needing fine-grained control over compositional elements.
Stars
485
Forks
39
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch"
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...