YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
梵高风格LoRA(Van Gogh Style LoRA)
基于Stable Diffusion v1-5训练的梵高风格LoRA,可生成具有梵高笔触、色彩和构图风格的图像。
训练信息
- 基础模型:runwayml/stable-diffusion-v1-5
- 训练数据:梵高经典作品(仅jpg图片,无txt依赖)
- 统一风格Prompt:
in <van-gogh> style - 训练步数:500步
- LoRA Rank:4
使用方法(Diffusers)
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
torch_dtype=torch.float32
).to("cuda")
# 加载LoRA(完整仓库ID)
pipe.load_lora_weights("imcodefool/van-gogh-style-lora", weight_name="pytorch_lora_weights.safetensors")
# 生成示例
prompt = "a wheat field with cypress trees, in <van-gogh> style"
image = pipe(
prompt,
num_inference_steps=50,
guidance_scale=7.5
).images[0]
image.show()
注意事项
- 触发词:
in <van-gogh> style - 风格强度:通过alpha值调整(0-1,默认0.8)
- 兼容模型:Stable Diffusion v1.x
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support