I wanted to create a model that has the quality of Flux without the limitations of NSFW content and does not require LoRa.
After a long time of work, I am now happy to be able to present my model to you.
(NSFW) Completely uncensored, allowing generation of erotic and very explicit images.
NSFW FLUX-Checkpoint
Training Configuration:
GPU: A6000
Dataset Size: 1500 images
Batch Size: 1
Optimizer: AdamW
Learning Rate: 1e-04
Total training steps: 30k
Training Duration: 17h+
Please note that all my FLUX checkpoint models are still experimental, so you might encounter some issues. If you do, please let me know in the comments section. Your feedback is valuable for future improvements!
GGUF-versions Uploded
Recommended Parameter :
Sampler : euler
Steps : 20+
CFG : 1
No VAE or CLIP is baked in. Use separate sources for those.
Minimum Parameter :
Sampler : euler
Steps : 16+
CFG : 1
LoRA's:
LoRA's are compatible with this checkpoint if they are trained using this model Flux Dev as the base model.
LoRA's trained on this model work with other Flux Dreambooth fine tune checkpoints.