News for hackers. Stuff that matters.

burkaygur

burkaygur on Hacker News

Re:The open weight Flux text to image model is next level on Thursday August 01, 2024 @02:08PM (#41131854)
Thanks for the feedback! Made some updates.
Re:The open weight Flux text to image model is next level on Thursday August 01, 2024 @01:37PM (#41131515)
hi friends! burkay from fal.ai here. would like to clarify that the model is NOT built by fal. all credit should go to Black Forest Labs (https://blackforestlabs.ai/) which is a new co by the OG stable diffusion team.

what we did at fal is take the model and run it on our inference engine optimized to run these kinds of models really really fast. feel free to give it a shot on the playgrounds. https://fal.ai/models/fal-ai/flux/dev

Show HN: Open-Source Image Model Leaderboard with Public Preference Data

Posted by burkaygur on Monday April 29, 2024 @07:03PM
from the show-hn dept.

https://imgsys.org/

We recently open sourced this public leaderboard and dataset with 50K+ preference data points across 20+ image models. Hoping that this is a useful resource for fine-tuning / preference optimization.Preference data is updated every day.Code for frontend: https://github.com/fal-ai/imgsys-publicPreference Data: https://huggingface.co/datasets/fal-ai/imgsys-results

( Read More... | 7 comments | 3 points | on HN )
Re:Fooocus: OSS for image generation by ControlNet author on Saturday August 12, 2023 @03:13PM (#37103278)
Made a Discord bot with this. Check it out here http://fooocus.ai
Re:Ask HN: Is the job market brutal? or is it just me? on Tuesday April 11, 2023 @02:53PM (#35529637)
We are hiring for Staff+ roles at fal.ai. Reach out to us:

https://featuresandlabels.notion.site/Join-us-at-fal-cf36c13...

Re:Dbt-fal: a dbt Python adapter with local code execution on Thursday January 12, 2023 @05:29PM (#34361166)
We built a dbt adapter that helps you run local Python code with your dbt project with any other data warehouse. You can see it here: https://github.com/fal-ai/fal/tree/main/adapter

It is very simple to use, but also very feature rich. For example, you can run each dbt model in an isolated Python environment and avoid dependency hell. We use isolate, an open source library we built to do that: https://github.com/fal-ai/isolate

Re:The Unbundling of Airflow on Tuesday February 15, 2022 @11:34PM (#30356398)
Looks like dbt Labs is working on a dbt Server that can translate your dbt-QL type queries into SQL. That way you can use different "building blocks" of SQL with the rest of your team. This becomes pretty powerful with the metrics layer that dbt just introduced.