Apache-2.0 model for text-to-image, instruction editing and in-context generation from multiple references
OmniGen2 is listed under AI Image Editing & Enhancement, in the Content & Media Generation category on Flocci AI Tools. Apache-2.0 model for text-to-image, instruction editing and in-context generation from multiple references. It is free, with no paid plan attached, and it lives at github.com.
OmniGen2 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.
OmniGen2 needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting.
OmniGen2 does 3 things the catalog singles out: Apache-2.0 model for text-to-image, instruction editing and in-context generation from multiple references; runs in about 17gb vram; cpu-offload mode under 3gb; free weights and gradio demo.
OpenPixels is the closest free alternative: it sits in the same AI Image Editing & Enhancement sub-category and is free. Segment Anything Playground, Affinity by Canva and BAGEL (ByteDance) also start free. The full list is on the alternatives page.
See the full list →