@fofrai

–

05 June 2025 12h02

Just increase the ratio of human input to (valuable) ai output. @swyx

5 June 2025

User Tests Wilhelm Scream Prompt with AI Image Generator

By

–

04 June 2025 16h49

Haha, I did try this:

> a wilhelm scream

(I was disappointed it didn't use the actual sound clip) pic.twitter.com/0sFLE8rYzj
— fofr (@fofrAI) 4 juin 2025

Haha, I did try this: > a wilhelm scream (I was disappointed it didn't use the actual sound clip)

4 June 2025

Flux-Kontext-Pro Model Surpasses Half Million Public Runs

By

–

04 June 2025 12h03

Already over half a million runs on our public flux-kontext-pro model. Dang y'all.

4 June 2025

Lucky Seed: Improving Portrait Generation Consistency

By

–

03 June 2025 23h50

Lucky seed? 1366738769
> make her look right, portrait view, lateral It didn't work with everyone, but it worked more than it usually does.

AI Model Resumes Prompt Generation Capability

By

–

03 June 2025 22h32

I think he's feeling better, he's prompting again.

Multiple Input Images Kontext Limitations Analysis

By

–

03 June 2025 22h00

My thoughts on using more than 2 input images with kontext, given current limitations.

Multimodal AI Image Processing Constraints and Trade-offs

By

–

03 June 2025 21h52

Right now it's constrained on kontext only taking a single image. You add multiple by concatenating images into a single one. The more images you pass in: – the less information gets kept from each one (fewer pixels per image)
– the harder it gets to prompt
– the more likely

Kontext Updates: Safety Controls and Multi-Image Model Support

By

–

03 June 2025 20h49

Shipped some small quality of life improvements to kontext today. You can now: – change the safety_tolerance (though image inputs are still limited to 2)
– pick an output format (jpg or png) Also, we have two multi-image models now.