NVlabs/Sana
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
This tool helps creative professionals and artists quickly generate high-resolution images and videos from text descriptions or existing images. It takes your textual prompts or initial images and transforms them into detailed visual content. Digital artists, content creators, and marketing professionals can use this to rapidly prototype ideas or produce visual assets.
5,000 stars. Actively maintained with 5 commits in the last 30 days.
Use this if you need to efficiently create high-quality images and videos for design, marketing, or entertainment, especially when working with demanding resolutions or looking for faster generation times.
Not ideal if you require hyper-realistic photo manipulation or precise control over every minute detail, as the generative nature might offer less direct artistic control than traditional editing software.
Stars
5,000
Forks
333
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NVlabs/Sana"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related models
FoundationVision/VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈]...
nerdyrodent/VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
huggingface/finetrainers
Scalable and memory-optimized training of diffusion models
AssemblyAI-Community/MinImagen
MinImagen: A minimal implementation of the Imagen text-to-image model
eps696/aphantasia
CLIP + FFT/DWT/RGB = text to image/video