Project Description
Generate a personalized avatar artwork images by fine-tuning stable diffusion on personal pictures
Goal for this Hackweek
Get a new fancy and unique avatar!
Resources
- https://huggingface.co/docs/diffusers/using-diffusers/sdxl
- https://huggingface.co/docs/diffusers/training/dreambooth
- https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sdxl.md
- https://civitai.com/models/133005/juggernaut-xl?modelVersionId=198530
Looking for hackers with the skills:
This project is part of:
Hack Week 23
Activity
Comments
-
about 1 year ago by STorresi | Reply
These are generated after a bespoke LoRA training using DreamBooth over the JuggernautXL model, which in turn is based on SDXL 1.0.
As you can see, hands are still tricky (a known issue of diffusion models, apparently), but I didn't try inpainting and img2img fine-tuning, which are supposed to be the go-to way to solve small issues like that. I must say the overall experience was quite painful due to the hardware requirements of SDXL and the amount of memory leaks in pytorch. A high-end consumer grade GPU like an NVIDIA 4080 with 16GB of VRAM often wasn't enough and ran OOM.
Similar Projects
Use AI tools to convert legacy perl scripts to bash by nadvornik
Description
Use AI tools to convert legacy perl scripts to bash
Goals
Uyuni project contains legacy perl scripts used for setup. The perl dependency could be removed, to reduce the container size. The goal of this project is to research use of AI tools for this task.
Resources
Results:
Aider is not the right tool for this. It works ok for small changes, but not for complete rewrite from one language to another.
I got better results with direct API use from script.
Gen-AI chatbots and test-automation of generated responses by mdati
Description
Start experimenting the generative SUSE-AI chat bot, asking questions on different areas of knowledge or science and possibly analyze the quality of the LLM model response, specific and comparative, checking the answers provided by different LLM models to a same query, using proper quality metrics or tools or methodologies.
Try to define basic guidelines and requirements for quality test automation of AI-generated responses.
First approach of investigation can be based on manual testing: methodologies, findings and data can be useful then to organize valid automated testing.
Goals
- Identify criteria and measuring scales for assessment of a text content.
- Define quality of an answer/text based on defined criteria .
- Identify some knowledge sectors and a proper list of problems/questions per sector.
- Manually run query session and apply evaluation criteria to answers.
- Draft requirements for test automation of AI answers.
Resources
- Announcement of SUSE-AI for Hack Week in Slack
- Openplatform and related 3 LLM models gemma:2b, llama3.1:8b, qwen2.5-coder:3b.
Notes
Foundation models (FMs):
are large deep learning neural networks, trained on massive datasets, that have changed the way data scientists approach machine learning (ML). Rather than develop artificial intelligence (AI) from scratch, data scientists use a foundation model as a starting point to develop ML models that power new applications more quickly and cost-effectively.Large language models (LLMs):
are a category of foundation models pre-trained on immense amounts of data acquiring abilities by learning statistical relationships from vast amounts of text during a self- and semi-supervised training process, making them capable of understanding and generating natural language and other types of content , to perform a wide range of tasks.
LLMs can be used for generative AI (artificial intelligence) to produce content based on input prompts in human language.
Validation of a AI-generated answer is not an easy task to perform, as manually as automated.
An LLM answer text shall contain a given level of informations: correcness, completeness, reasoning description etc.
We shall rely in properly applicable and measurable criteria of validation to get an assessment in a limited amount of time and resources.
AI for product management by a_jaeger
Description
Learn about AI and how it can help myself
What are the jobs that a PM does where AI can help - and how?
Goals
- Investigate how AI can help with different tasks
- Check out different AI tools, which one is best for which job
- Summarize learning
Resources
- Reading some blog posts by PMs that looked into it
- Popular and less popular AI tools
Work is done SUSE internally at https://confluence.suse.com/display/~a_jaeger/Hackweek+25+-+AI+for+a+PM and subpages.
Learn how to integrate Elixir and Phoenix Liveview with LLMs by ninopaparo
Description
Learn how to integrate Elixir and Phoenix Liveview with LLMs by building an application that can provide answers to user queries based on a corpus of custom-trained data.
Goals
Develop an Elixir application via the Phoenix framework that:
- Employs Retrieval Augmented Generation (RAG) techniques
- Supports the integration and utilization of various Large Language Models (LLMs).
- Is designed with extensibility and adaptability in mind to accommodate future enhancements and modifications.
Resources
- https://elixir-lang.org/
- https://www.phoenixframework.org/
- https://github.com/elixir-nx/bumblebee
- https://ollama.com/
Use local/private LLM for semantic knowledge search by digitaltomm
Description
Use a local LLM, based on SUSE AI (ollama, openwebui) to power geeko search (public instance: https://geeko.port0.org/).
Goals
Build a SUSE internal instance of https://geeko.port0.org/ that can operate on internal resources, crawling confluence.suse.com, gitlab.suse.de, etc.
Resources
Repo: https://github.com/digitaltom/semantic-knowledge-search
Public instance: https://geeko.port0.org/
Results
Internal instance:
I have an internal test instance running which has indexed a couple of internal wiki pages from the SCC team. It's using the ollama (llama3.1:8b
) backend of suse-ai.openplatform.suse.com to create embedding vectors for indexed resources and to create a chat response. The semantic search for documents is done with a vector search inside of sqlite, using sqlite-vec.