News for hackers. Stuff that matters.

gorkemyurt

wow! latency is insane
Re:The open weight Flux text to image model is next level on Friday August 02, 2024 @07:59AM (#41138104)
also no signup for the optimized endpoint on fal https://fal.ai/models/fal-ai/flux/schnell
Re:Stable Cascade on Tuesday February 13, 2024 @01:16PM (#39360800)
we have an optimized playground here: https://www.fal.ai/models/stable-cascade
Re:Real Time Sketching –> Image Generation on Tuesday November 14, 2023 @06:34PM (#38271336)
thanks for the feedback codingwave! yes there is so much to add! wanted to highlight the potential with this demo
Re:Generate Portraits with the Style of Fernando Botero on Thursday September 21, 2023 @03:40PM (#37603057)
Earlier this week, we lost one of my favorite artists, Fernando Botero. I've always admired the whimsical and accessible nature of his artwork.

We trained a LoRA on his art style, and I am truly impressed by how effectively it captures his essence.

Some of my favorites: https://twitter.com/gorkemyurt/status/1704903418035454448

incredible job @ykhli! thank you for the fal.ai mention on the stack! https://github.com/a16z-infra/ai-town#stack

for anyone eager to generate their own simulation head to https://serverless.fal.ai/lora to create your own pixel art game characters

Re:Segment anything and Stable Diffusion showcase app on Tuesday May 09, 2023 @08:40PM (#35882220)
thanks for the interest, had some downtime but should be working now!
Re:Segment anything and Stable Diffusion showcase app on Tuesday May 09, 2023 @05:36PM (#35880701)
Sharing our reference application that we built using Stable Diffusion and Segment Anything.

Stable Diffusion + Segment Anything - https://www.editanything.ai/ (try out the app!)

We believe chaining different models can lead to impressive user experiences and as an AI product owner you can really differentiate yourself from others if you use several models in creative ways.

https://github.com/fal-ai/edit-anything-app

In the example there is python code to do the model inference as well as the javascript code to build the application. I believe this would be a great reference implementation for people trying to build their own AI apps.

Made a short video explaining the application: https://youtu.be/ob_WOogJn_A

If there is interest would love to do a walkthrough of the codebase with a video as well!

Re:Building language model powered pipelines with dbt on Thursday February 23, 2023 @06:55PM (#34918612)
LLM models can still be leveraged to solve everyday problems of analytics engineers and data engineers. Transformation of unstructured text is a notoriously complicated problem almost every business faces every day.

Would you jump on the AI bandwagon if I told you that you that you can get rid of that 15 line regular expression that you keep around to do entity resolution or detect addresses?

Re:The Unbundling of Airflow on Tuesday February 15, 2022 @06:13PM (#30354219)
Hi, I am the author of the post which parts did you find hard to follow?
Re:The Unbundling of Airflow on Tuesday February 15, 2022 @05:48PM (#30353943)
High Resolution Version of the diagram if anyone is interested

https://drive.google.com/file/d/1btZ0yck9SdgsUdNom0WXgHcSQvO...

Re:Are cryptocurrencies to blame for high GPU prices? on Saturday January 01, 2022 @01:23PM (#29761062)
AI, VR and crypto all require GPUs and coming of age at the same time..
Re:I hope work from home continues on Tuesday April 06, 2021 @11:58AM (#26713470)
How do you carry your monitor? this has been a problem for me during covid. also there is the work chair problem..
Re:Who Owns the Nile? on Friday April 02, 2021 @04:34PM (#26675679)
"Egypt's military is the strongest in the region minus Israel." and minus Turkey

Older »