TheLastBen / fast-stable-diffusion

fast-stable-diffusion + DreamBooth
MIT License
7.52k stars 1.31k forks source link

Connection errors out immediately after changing models on colab #2450

Open holma91 opened 1 year ago

holma91 commented 1 year ago

I get the following output from the "Start Stable Diffusion" cell:

2023-08-08 06:42:55,058 - ControlNet - INFO - ControlNet v1.1.234
ControlNet preprocessor location: /content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-webui-controlnet/annotator/downloads
2023-08-08 06:42:55,603 - ControlNet - INFO - ControlNet v1.1.234
Loading weights [31e35c80fc] from /content/gdrive/MyDrive/sd/stable-diffusion-webui/models/Stable-diffusion/sd_xl_base_1.0.safetensors
Running on local URL: https://b724-34-80-209-32.ngrok-free.app/
✔ Connected
Startup time: 34.5s (import torch: 19.8s, import gradio: 2.6s, start: 0.3s, setup paths: 3.4s, other imports: 1.9s, list SD models: 0.7s, load scripts: 3.8s, create ui: 1.2s, gradio launch: 0.4s, add APIs: 0.2s).
Loading weights [15012c538f] from /content/gdrive/MyDrive/sd/stable-diffusion-webui/models/Stable-diffusion/realisticVisionV51_v51VAE.safetensors
Creating model from config: /content/gdrive/MyDrive/sd/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Creating model from config: /content/gdrive/MyDrive/sd/stablediffusion/generative-models/configs/inference/sd_xl_base.yaml
Applying attention optimization: xformers... done.
Model loaded in 31.2s (create model: 2.6s, apply weights to model: 21.4s, apply half(): 2.1s, load VAE: 0.2s, move model to device: 4.0s, load textual inversion embeddings: 0.2s, calculate empty prompt: 0.7s).
^C

Have tried with and without ngrok, no difference.

TheLastBen commented 1 year ago

use High-RAM runtime