A personal version of the great workflow-flux-sigma-vision-alpha1---t2i---v1-slow-0zYNCa5vKyE2ccDxynZC-caiman_thirsty_60-openart.ai.

I adapted the original previous workflow into an upscaler that enhances the sharpness of characters while reinforcing their consistency.

Why? Because this fine tuning fully leverages the potential of FLUX and video models by providing input images optimized for maximum rendering. Moreover, high resolution offers unprecedented creative freedom by enabling the creation of various shots from a single image—be it a wide shot, a close-up of the face, or an extreme close-up of an eye. This results in more dynamic sequences and facilitates the integration of cinematic codes.

Flux de-distilled model FP16 + VAE: https://civarchive.com/models/1223425/sigma-vision

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

Original model : ComfyUI : https://github.com/comfyanonymous/ComfyUI