These are simply a merged in version of SNOFS on top of Krea 2 Raw or Flux 2 Klein 9b Base or Distilled. You can use it to generate without using the SNOFS lokr, can't use lokrs for whatever reason, or want to train on top of them instead of the base model (so characters or styles come out well). I suppose you could also use them to generate on Civitai - if you want to run the Krea version as turbo on Civitai use one of the turbo extracted loras with it (and then CFG 1, 8 steps with Euler/Simple).
For full details on how best to use this model please check out the lokr page: https://civarchive.com/models/1972981/sex-nudes-other-fun-stuff-snofs
Both the lokr and this trained model are released under this license:
https://huggingface.co/Ashen3/SNOFS
Want to support my work or help fund the training of this dataset on other models? Join the Patreon in my profile, and if you do - thank you!
SNOFS Krea 1.3D bf16 and int8 convrot are both available as variants.
Description
FAQ
Comments (10)
Unfortunately, this model won't be usable by many users: it's not FP8 and it's not 4-step - people don't have enough RAM, they don't have enough VRAM, they have slow video cards, and connecting LoRA slows down generation by half.
V1.2 distilled is FP8, and there is also an BF16 distilled version V1. These can generate in 4 steps out of the box.
9b Base (V1.0, 1.3 and 1.4) is for training LoRa/LoKr, but it can also generate in 4 steps if you add the Turbo LoRa to the workflow (CFG 1 for fastest generation).
You are right that VRAM is a bottleneck for many. Offloading is an option for 9b Base, for a decent system, but that is slow.
Maybe a 4b model will also be released(?)
@aising23 I don't want to use klein 4B. I have GTX 1050 with 4 GB VRAM and still can use klein 9B FP8 distilled, 768x512 generation takes about 1 minute - it's ok.
Please make 4 step turbo versions in FP8, because using turbo LoRA on klein-9b-base slows down generation by half, and converting to FP8 when loading the model doesn't work for some reason. Thank you in advance!!!
Love your model but wish you kept on going with the distilled versions. Especially with the omni workflows out there that work with ComfyUI-Flux2Klein-Enhancer its hard to make the base model perform just as good. Currently stuck on 1.2 because 1.4 wont play nice with those nodes.
I'll get it up sometime soon.
@Ashen3 distilled and FP8 also, please :)
1.4 is up.
@Ashen3 you are awesome
Is there a recommended workflow for this?
Details
Files
snofsSexNudesAndOther_v14Klein9bBase.safetensors
Mirrors
snofsSexNudesAndOtherFunStuff_v14Base-bf16.safetensors
flux-2-klein-base-9b.safetensors
snofsSexNudesAndOtherFunStuff_v14Base-bf16.safetensors
snofsSexNudesAndOtherFunStuff_v14Base.safetensors
flux-2-klein-base-9b.safetensors
Flux2Klein9B_base-bf16_SNOFS_v1.4.safetensors
snofsSexNudesAndOtherFunStuff_v14Base.safetensors