Open rando128 opened 2 months ago
polalbacar
commented
2 months ago @rando128 and that worked for you?
When I run the command:
cog predict -i image=@test_images/bedroom_3.jpg -i prompt="A bedroom with a bohemian spirit centered around a relaxed canopy bed complemented by a large macrame wall hanging. An eclectic dresser serves as a unique storage solution while an array of potted plants brings life and color to the room"
I face the following issue:
Unknown option -i
rando128
commented
2 months ago On windows 11, WSL2, I do need the extra -i to make it work
rando128@dev:/mnt/AI/sd-interior-design$ cog predict -i image=@test_images/bedroom_3.jpg -i prompt="A bedroom with a bohemian spirit centered around a relaxed canopy bed complemented by a large macrame wall hanging. An eclectic dresser serves as a unique storage solution while an array of potted plants brings life and color to the room"
Building Docker image from environment in cog.yaml...
[+] Building 2.1s (13/13) FINISHED docker:default
=> [internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 439B 0.0s
=> resolve image config for docker.io/docker/dockerfile:1.4 1.0s
=> CACHED docker-image://docker.io/docker/dockerfile:1.4@sha256:9ba7531bd80fb0a858632727cf7a112fbfd19b17e94c4e84ced81e24ef1a0dbc 0.0s
=> [internal] load .dockerignore 0.0s
=> => transferring context: 374B 0.0s
=> [internal] load metadata for r8.im/cog-base:cuda11.8-python3.11 0.9s
=> [internal] load build context 0.0s
=> => transferring context: 404B 0.0s
=> [stage-0 1/5] FROM r8.im/cog-base:cuda11.8-python3.11@sha256:0236faa635dfeb9bd0c89b1451ff9e2cb307a200b1ba6f6f84e088c8bf56000f 0.0s
=> CACHED [stage-0 2/5] RUN --mount=type=cache,target=/var/cache/apt,sharing=locked apt-get update -qq && apt-get install -qqy && rm -rf /var/lib/apt/lists/* 0.0s
=> CACHED [stage-0 3/5] COPY .cog/tmp/build20240823211127.9959563440740036/requirements.txt /tmp/requirements.txt 0.0s
=> CACHED [stage-0 4/5] RUN pip install -r /tmp/requirements.txt 0.0s
=> CACHED [stage-0 5/5] WORKDIR /src 0.0s
=> preparing layers for inline cache 0.0s
=> exporting to image 0.0s
=> => exporting layers 0.0s
=> => writing image sha256:0dcab56e1c6b6f73014bd9efb2d3d02d55a692b2c246c3c635c6b7cd96d6bb61 0.0s
=> => naming to docker.io/library/cog-sd-interior-design-base 0.0s
Starting Docker image cog-sd-interior-design-base and running setup()...
The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.
0it [00:00, ?it/s]
/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/huggingface_hub/file_download.py:1150: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
The config attributes {'dropout': 0.0, 'sample_size': 32} were passed to ControlNetModel, but are not expected and will be ignored. Please verify your config.json configuration file.
......
I think there is a typo in the basic prediction command. I had to add
-ibefore the prompt part for the command to be correctly interpreted.cog predict -i image=@test_images/bedroom_3.jpg -i prompt="A bedroom with a bohemian spirit centered around a relaxed canopy bed complemented by a large macrame wall hanging. An eclectic dresser serves as a unique storage solution while an array of potted plants brings life and color to the room"