alimama-creative/FLUX.1-Turbo-Alpha

Puede usarse directamente con Diffusers cargando FLUX.1-dev como modelo base y aplicando este adaptador LoRA. La configuración recomendada por la tarjeta del modelo usa 8 pasos de inferencia y guidance_scale=3.5.

import torch
from diffusers.pipelines import FluxPipeline

model_id = "black-forest-labs/FLUX.1-dev"
adapter_id = "alimama-creative/FLUX.1-Turbo-Alpha"

pipe = FluxPipeline.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16
)
pipe.to("cuda")
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()

prompt = "A DSLR photo of a shiny VW van that has a cityscape painted on it. A smiling sloth stands on grass in front of the van and is wearing a leather jacket, a cowboy hat, a kilt and a bowtie. The sloth is holding a quarterstaff and a big book."

image = pipe(
    prompt=prompt,
    guidance_scale=3.5,
    height=1024,
    width=1024,
    num_inference_steps=8,
    max_sequence_length=512).images[0]