yandex-research/adaptive-diffusion
[CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models
This project helps content creators and digital artists generate high-quality images from text descriptions more efficiently. You provide a text prompt describing the desired image, and it intelligently decides whether a fast, 'student' image model is sufficient or if a slower, more detailed 'teacher' model is needed for better results. The output is a high-fidelity image that balances speed and visual quality.
No commits in the last 6 months.
Use this if you need to generate high-quality images from text prompts and want to optimize for a balance between speed and image fidelity, rather than always waiting for the slowest, most detailed model.
Not ideal if you prioritize absolute fastest image generation regardless of quality, or if you exclusively need the highest possible quality for every image without any time constraints.
Stars
33
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yandex-research/adaptive-diffusion"
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...