触发词

请使用采用s456风格；触发漫画风格图像生成。

博客

阅读我们在Medium平台的技术文章

推理代码

import torch  
from diffusers import DiffusionPipeline  

model_id = 'black-forest-labs/FLUX.1-dev'  
adapter_id = 'Rachit22/simpletuner-flux-manhawa'  
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)  # 直接加载为bf16格式  
pipeline.load_lora_weights(adapter_id)  

prompt = "采用s456风格；身着灰色盔甲、蓝眼发光的强大男性猎人，暗影召唤物在身后升起，场景设定在布满破碎雕像的幽暗地牢，高细节"  

# 可选：量化模型以节省显存  
# 注意：训练时已对模型量化，建议推理时保持相同设置  
from optimum.quanto import quantize, freeze, qint8  
quantize(pipeline.transformer, weights=qint8)  
freeze(pipeline.transformer)  

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')  # 管道已处于目标精度  
model_output = pipeline(  
    prompt=prompt,  
    num_inference_steps=20,  
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),  
    width=1024,  
    height=1024,  
    guidance_scale=3.0,  
).images[0]  

model_output.save("output.png", format="PNG")  

联合开发者：Riya Ranjan