prithivMLmods/Canopus-LoRA-Flux-Anime

Instalación y uso con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    dtype=torch.bfloat16,
    device_map="cuda"
)
pipe.load_lora_weights("prithivMLmods/Canopus-LoRA-Flux-Anime")

prompt = "Anime ((masterpiece,best quality, detailed)), outdoor,wind_lift, souryuu asuka langley, interface headset, red bodysuit, (realistic:1.3)"
image = pipe(prompt).images[0]

Configuración alternativa mostrada en la tarjeta del modelo:

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "prithivMLmods/Canopus-Anime-Art-Flux-LoRA"
trigger_word = "Anime"
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Usa Anime como palabra de activación en el prompt. Ejemplos de prompts:

Anime ((masterpiece,best quality, detailed)), outdoor,wind_lift, souryuu asuka langley, interface headset, red bodysuit, (realistic:1.3)

Anime theme masterpiece,best quality,1girl,solo,looking at viewer, fur (clothing), black hair, black legwear,(electric guitar:1.4), reflection, splash, droplets, rust, sparks, asphalt, ground vehicle, sports car, super car, mechanical,burning, playing instrument, livestream.