stablediffusion吧 关注:27,378贴子:94,175
  • 0回复贴,共1

只要使用SDXL inpainting 模型就报错

只看楼主收藏回复

普通SDXL模型正常,只要使用修复模型就报错,VAE不加载也是,换了几个大模型也是一样。
1.5没有问题。
报错信息如下:
To create a public link, set `share=True` in `launch()`.
Startup time: 20.9s (prepare environment: 10.1s, import torch: 2.8s, import gradio: 0.8s, setup paths: 0.6s, initialize shared: 0.2s, other imports: 0.4s, load scripts: 2.4s, create ui: 0.7s, gradio launch: 2.3s, add APIs: 0.5s, app_started_callback: 0.1s).
Loading VAE weights specified in settings: C:\sd-webui-v47_2\models\VAE\sdxl_vae.safetensors
Applying attention optimization: xformers... done.
Model loaded in 6.0s (load weights from disk: 0.4s, create model: 0.9s, apply weights to model: 4.2s, load VAE: 0.1s, move model to device: 0.1s, calculate empty prompt: 0.2s).
*** Error completing request
*** Arguments: ('task(jis5801ls7cloqj)', 4, '', '', [], None, None, None, None, None, <PIL.Image.Image image mode=RGB size=720x1280 at 0x18888CDDFF0>, <PIL.Image.Image image mode=RGBA size=720x1280 at 0x18888CDE080>, 35, 'Euler a', 4, 0, 1, 1, 1, 7, 1.5, 0.75, 0.0, 1280, 720, 1, 0, 0, 32, 0, '', '', '', [], False, [], '', <gradio.routes.Request object at 0x0000018888EC04F0>, 0, False,


IP属地:安徽1楼2024-07-30 13:42回复