Can we use other SD models (and Loras) on Quick Deploy serverless?
Hello everyone,
I tried the quick deploy option for SD Automatic1111. And the speed of generation is very good. I tried to modify the original model to use another one. In the Dockerfile, I replaced the original model with Cyber_Realisic model. I only changed the line where the civitai link is (you can see the picture).
When I tried to create the Docker image I got an issue:
ERROR: failed to solve: process "/bin/bash -o pipefail -c cd /stable-diffusion-webui && python cache.py --use-cpu=all --ckpt /model.safetensors" did not complete successfully: exit code: 1
Do you know if it's possible to use different models with this deployment and can I add Loras to it?
Thank you in advance
4 Replies
@CR-TZM Hello friend, could I perhaps contact you, I am doing this for a client and not able to figure it out either.
@CR-TZM you probably not download correct file then. Civatic website now requires api key to access files
Where do you add loras here friend?
The entire thing is very confusing.
I finally use another method which is using a network volume every time.
Yes you're probably right, thank you for your answer