Since this is a dedistilled version of "Flux schnell", Apache 2.0 license applies making it free to use commercially.This fine tuned checkpoint is based on Flux schnell de-distilled thus requires a special comfyUI workflow and won't work very well with standard Flux dev workflows since it's uisng real CFG.This checkpoint has been trained on high resolution images that have been processed to enable the fine-tune to train on every single detail of the original image, thus working around the 1024x1204 limitation, enabling the model to produce very fine details during tiled upscales that can hold up even in 32K upscales. The result, extremely detailed and realistic skin and overall realism at an unprecedented scale.This first alpha version has been trained on male subjects only but elements like skin details will likely partically carry over though not confirmed.Training for female subjects happening as we speak.Highest quality slow version:<a target="_blank" rel="ugc" href="https://openart.ai/workflows/caiman_thirsty_60/flux-sigma-vision-alpha1---t2i---v1-slow/0zYNCa5vKyE2ccDxynZC">https://openart.ai/workflows/caiman_thirsty_60/flux-sigma-vision-alpha1---t2i---v1-slow/0zYNCa5vKyE2ccDxynZC</a>Turbo version with shamelessly good quality!!!:<a target="_blank" rel="ugc" href="https://openart.ai/workflows/caiman_thirsty_60/flux-sigma-vision-alpha1---t2i---v1-turbo/GIcCaNySArtfrQGbgyQm">https://openart.ai/workflows/caiman_thirsty_60/flux-sigma-vision-alpha1---t2i---v1-turbo/GIcCaNySArtfrQGbgyQm</a>Resources:Lora:Fast Lora: <a target="_blank" rel="ugc" href="https://huggingface.co/ostris/OpenFLUX.1/blob/main/openflux1-v0.1.0-fast-lora.safetensors">https://huggingface.co/ostris/OpenFLUX.1/blob/main/openflux1-v0.1.0-fast-lora.safetensors</a>Turbo Lora: <a target="_blank" rel="ugc" href="https://huggingface.co/alimama-creative/FLUX.1-Turbo-Alpha">https://huggingface.co/alimama-creative/FLUX.1-Turbo-Alpha</a>Text encoders:ViT-L-14-BEST-smooth-GmP-ft:<a target="_blank" rel="ugc" href="https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/resolve/main/ViT-L-14-BEST-smooth-GmP-ft.safetensors?download=true">https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/resolve/main/ViT-L-14-BEST-smooth-GmP-ft.safetensors?download=true</a>t5-v1_1-xxl:<a target="_blank" rel="ugc" href="https://huggingface.co/city96/t5-v1_1-xxl-encoder-bf16/resolve/main/model.safetensors?download=true">https://huggingface.co/city96/t5-v1_1-xxl-encoder-bf16/resolve/main/model.safetensors?download=true</a>Clip G:<a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3.5-large/resolve/main/text_encoders/clip_g.safetensors?download=true">https://huggingface.co/stabilityai/stable-diffusion-3.5-large/resolve/main/text_encoders/clip_g.safetensors?download=true</a>Recommended settings:Without Turbo and Fast LoraCFG: 2-4Steps: 50-60With Turbo and Fast LoraCFG: 2-4Steps: 8-16Turbo Lora weight: 1Fast Lora weight: 0.33This Flux variant works with negative prompts so use them if you want to. Negative prompt will work with and without the Turbo Lora.

Flux Sigma Vision Alpha1

fluxSigmaVision_q2K.gguf

Q2_K

Q3_K_S

Q4_0

Q4_1

Q4_K_S

Q5_0

Q5_1

Q5_K_S

Q6_K

Q8_0

fp16

Files with SHA256: 20ae04e34c3bdd5ec20696d580a98bbd2317b204a632a05fefa6833d88b21f22