Flux-Sigma-Vision-Lora

Flux Sigma Vision Lora

<Gallery /> <table> <tr> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/yDMyFsq4m7MAr7e2FN3DN.jpeg" width="100%"></td> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/HDY94CIVWYOnWYH0ob8eb.jpeg" width="100%"></td> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/ivQEs4ZTMczF4vWNaabnC.jpeg" width="100%"></td> </tr> <tr> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/aM8lbXr6FRed8d7QQFxzg.jpeg" width="100%"></td> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/0jKsmwji10B3cg4bAb_0v.jpeg" width="100%"></td> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/pdxMgRG2U33MBjnJcCa-m.jpeg" width="100%"></td> </tr> <tr> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/MxdjDFPMECE5mljKo5ENA.jpeg" width="100%"></td> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/k2og9FBwju3sy-CGjVHDK.jpeg" width="100%"></td> <td><img src="https://cdn-uploads.huggingface.co/production/uploads/664a3d3bb5e5f95dc6e86a6d/ommw_wyr8POqbP-8TCq8I.jpeg" width="100%"></td> </tr> </table>

Model description

This Lora is extraxted from a fine tuned checkpoint, based on Flux dev de-distilled.

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:

• https://openart.ai/workflows/caiman_thirsty_60/flux-sigma-vision-alpha1---t2i---v1-slow/0zYNCa5vKyE2ccDxynZC

• Turbo version with shamelessly good quality!!!:

• https://openart.ai/workflows/caiman_thirsty_60/flux-sigma-vision-alpha1---t2i---v1-turbo/GIcCaNySArtfrQGbgyQm

Resources:

Lora:

Fast Lora:

• https://huggingface.co/ostris/OpenFLUX.1/blob/main/openflux1-v0.1.0-fast-lora.safetensors

Turbo Lora:

• https://huggingface.co/alimama-creative/FLUX.1-Turbo-Alpha

Text encoders:

ViT-L-14-BEST-smooth-GmP-ft:

• https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/resolve/main/ViT-L-14-BEST-smooth-GmP-ft.safetensors?download=true

t5-v1_1-xxl:

• https://huggingface.co/city96/t5-v1_1-xxl-encoder-bf16/resolve/main/model.safetensors?download=true

Clip G:

• https://huggingface.co/stabilityai/stable-diffusion-3.5-large/resolve/main/text_encoders/clip_g.safetensors?download=true

Recommended settings:

Without Turbo and Fast Lora

CFG: 2-4

Steps: 50-60

With Turbo and Fast Lora

CFG: 2-4

Steps: 8-16

Turbo Lora weight: 1

Fast Lora weight: 0.33

🧪 Example Usage

Use the following Python code to generate images with this LoRA using the Diffusers library:

import torch
from diffusers import FluxPipeline

# Load the base model
pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell",
    torch_dtype=torch.float16,
    use_auth_token=True  # Make sure you're logged into Hugging Face CLI
).to("cuda")

# Load the LoRA weights from Hugging Face Hub
pipe.load_lora_weights("shemayons/Flux-Sigma-Vision-Lora", weight_name="flux_sigma_vision_lora.safetensors")

# Optionally fuse LoRA weights with a custom scale
pipe.fuse_lora(lora_scale=0.8)

# Define your prompt
prompt = "a futuristic cityscape at sunset"
negative_prompt = "low quality, blurry"

# Generate the image
image = pipe(prompt=prompt, negative_prompt=negative_prompt, num_inference_steps=30).images[0]

# Show the result
image.show()

This Flux variant works with negative prompts so use them if you want to. Negative prompt will work with and without the Turbo Lora.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.