VinAIResearch/DiMSUM
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation (NeurIPS 2024)
DiMSUM is a tool for researchers and practitioners in generative AI who need to create high-quality images. It takes raw image data and generates new, highly realistic images. This is for professionals like AI researchers, computer vision engineers, and content creators working with synthetic media.
No commits in the last 6 months.
Use this if you need to generate high-quality, realistic images for datasets like CelebA HQ, LSUN Church, or ImageNet-1K, and prioritize fast training convergence and state-of-the-art results.
Not ideal if you are looking for a simple, out-of-the-box image generation tool without diving into model training and evaluation.
Stars
43
Forks
6
Language
Python
License
BSD-3-Clause
Category
Last pushed
Feb 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VinAIResearch/DiMSUM"
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...