FLUX.2 autoencoder, single file (mirror)
The single-file FLUX.2 VAE that stable-diffusion.cpp needs for both FLUX.2 [dev] and FLUX.2 klein, mirrored from Comfy-Org/flux2-dev.
Unsloth Studio fetches this on the no-GPU (native sd.cpp) path. It used to come straight from the community repack; a rename or a takedown there turns every CPU FLUX.2 load into a 404, so it is mirrored here. The weights are unmodified: byte for byte the file of the same name in the source repo.
| File | Size | Upstream model | Licence |
|---|---|---|---|
split_files/vae/flux2-vae.safetensors |
0.31 GiB | black-forest-labs/FLUX.2-dev (autoencoder) | Apache-2.0 |
Licence: Apache-2.0, and that is deliberate
The rest of FLUX.2 [dev] is under the FLUX Non-Commercial License. The autoencoder is not. Black Forest Labs released it separately and says so in their own repository: "The autoencoder is released under Apache 2.0" (github.com/black-forest-labs/flux2).
That matters here because FLUX.2 klein 4B is itself Apache-2.0 and needs this VAE. Bundling it with the non-commercial conditioner would have put a permissive file behind a non-commercial label. So it lives on its own, and the non-commercial half is at unsloth/FLUX.2-dev-ComfyUI.
Full text in LICENSE,
attribution and the statement of what the repack changed in
NOTICE. Not an official Black
Forest Labs or ComfyUI product, and not endorsed by either.