Add cog.yaml and predict.py for usage with Replicate and Docker #39
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
December 1, 2024 01:14
- Add time tracking for image generation - Save multiple images from a list of prompts - Calculate and display average time per image - Improve code readability and organization
|
That is amazing. I will review your pr to see if it is appropriate in this repo. Thanks for your contributions! |
added 4 commits
December 8, 2024 21:06
- Implement login and logout functionality - Enhance security with password hashing - Address issue mit-han-lab#42 for user access control
- Include safety_checker module for NSFW detection - Adjust server.py to use safety checker with adjustable sensitivity - Modify Dockerfile to copy safety_checker directory - Update server command to use module syntax
|
I have now modified the branch to work directly with Docker. If you are interested in the Docker stuff without the replicate/cog things I could clean this PR up. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I'm not totally sure if you want to have this in your repository but I figured I'd make a pull request anyway.
This PR adds the necessary configuration and code to deploy the model on Replicate:
cog.yamlwith CUDA 12.4 and Python 3.11 setuppredict.pywith Replicate-compatible inference codeexample.pywith batch processing supportThe implementation supports configurable image dimensions, inference steps, and seeds. Sequential CPU offloading is enabled by default for better memory management.
Let me know if you need any clarification or changes.
It is deployed here: https://replicate.com/pollinations/flux-schnell-svdquant