ddPn08

I see. I certainly didn't consider that risk. I'll try it myself for now. Thank you very much!

If the model is diffusers format, local ones can also be used.

@koukei46124 ターミナルのログ見せてもらえますか？

これはdockerコンテナ内だからですね。基本的にdockerコンテナ内からwindowsのフォルダすべてにはアクセスできません（パスの形式もwindowsの物は使えないです。） たとえばdocker-compose.ymlを ``` version: '3.9' services: lsmith: build: context: . dockerfile: ./docker/Dockerfile.lite ports: - 8000:8000 volumes: - ./docker-data/models:/app/models - ./docker-data/outputs:/app/outputs - ./docker-data/diffusers:/diffusers environment: - COMMANDLINE_ARGS=--skip-build-frontend - UVICORN_ARGS=--host 0.0.0.0 deploy: resources:...

After cloning run the following command to initialize the submodule. ```sh cd Lsmith git submodule update --init --recursive ```

``` docker compose up --build ``` Please try again with the above command.

Closing this issue as the project has been significantly updated. Please reopen if you still have problems.

We are currently implementing a way to build the tensorrt engine from ckpt and vae.pt files.

@greyphilosophy You have to enable "control_net_no_detectmap" in the settings tab.

@FizzleDorf It is displayed only in the img2img tab. Also, since this is a pull request, the latest version of this repository does not reflect this change.