AI Toolkit

license

MIT(OSI)

source

public(ostris/ai-toolkit)

core-gated

ungated(no enterprise or ee path in the repository root

MIT, an OSI licence, with the full source public and the shipped code in this repository. The LICENSE body was read in full: the stock MIT text, with no appended condition. No enterprise or ee path in the repository root; the readme's ostris cloud section offers rented gpus to fund development and an affiliate link, not a paid tier of the software.

• https://raw.githubusercontent.com/ostris/ai-toolkit/main/LICENSE recorded 2026-08-31

  LICENSE body, read in full: the stock MIT licence text, carrying no appended term or additional condition.

• https://raw.githubusercontent.com/ostris/ai-toolkit/main/README.md recorded 2026-08-31

  README, read for the distribution and gating question: it describes installing and running the code from this repository and names no enterprise, paid or licence-gated build. Its Ostris Cloud section offers rented GPUs to fund the project, alongside a RunPod affiliate link, rather than a paid tier of the software itself.

No package registry carries this product, so stars are the only available signal and the band is capped at 3 by the instrument. 11,860 stargazers places it at level 3. Stars measure attention rather than use, which is why the confidence is low.

• https://api.github.com/repos/ostris/ai-toolkit recorded 2026-08-31

  Repo metadata for ostris/ai-toolkit: stargazers_count 11860, archived false, pushed_at 2026-08-30.

A diffusion-specialist trainer with wide and current model coverage but an adapter-centric method set and no distributed-training story. It is scored against onetrainer rather than the category anchor because megatron-lm's parallelism-and-scale ladder says nothing about a consumer-GPU diffusion trainer; 3 is where this category puts a solid method catalogue at limited scale, as it does for litgpt and torchtune.

• https://raw.githubusercontent.com/ostris/ai-toolkit/main/README.md recorded 2026-08-31

  Supported Models section lists FLUX.1, FLUX.2 dev and klein-base 4B/9B, Flex.1, Flex.2, Chroma, Lumina2 and Qwen-Image under Image, with further Instruction/Edit, Video, Audio and Experimental groups; the README documents LoRA and LyCORIS training and an AI Toolkit UI.