Apache-2.0 linear-diffusion family for text-to-image up to 4K, with SANA-Sprint one-step generation
SANA (NVIDIA) is listed under AI Image Generation, in the Content & Media Generation category on Flocci AI Tools. Apache-2.0 linear-diffusion family for text-to-image up to 4K, with SANA-Sprint one-step generation. It is free, with no paid plan attached, and it lives at github.com.
SANA (NVIDIA) is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
SANA (NVIDIA) needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting.
SANA (NVIDIA) does 3 things the catalog singles out: Apache-2.0 linear-diffusion family for text-to-image up to 4k, with sana-sprint one-step generation; sana-video 2.0 (5b/14b) for 720p text-to-video (aug 2026); free public demo at nv-sana.mit.edu and hugging face spaces.
Bing Image Creator is the closest free alternative: it sits in the same AI Image Generation sub-category and is free. PicLumen, Qwen-Image and ComfyUI also start free. The full list is on the alternatives page.
See the full list →