We will have AGI when AI can write comedy.
@fofrai
-
Omni is skilled at texts
By
–
Did you know Omni is good at text? pic.twitter.com/ey037ZlXIz
— fofr (@fofrAI) 16 juin 2026Did you know that Omni is skilled at texts?
-
Example startup videos with audio agent skill
By
–
Example starter videos (you can download these to try).
— fofr (@fofrAI) 15 juin 2026
I have an agent skill that makes them and strips out any audio. pic.twitter.com/3H6AJvBvltExample startup videos (you can download them to try). I have an agent skill that creates and removes all audio.
-
Fun trick to force Omni to fill black frames
By
–
Here's a fun hack that nudges Omni into a style space that it's hard to get to with just a prompt:
— fofr (@fofrAI) 15 juin 2026
– take a video and trim it to a few seconds at the start/end/both
– pad the rest of the frames to be black (24fps, 720p)
– prompt the model: "fill in the black frames" (or similar)… pic.twitter.com/hm0RcCaBGZHere is a fun trick that pushes Omni into a stylistic space hard to reach with a simple prompt: – take a video and cut it to a few seconds at the start/end/both – fill the remaining frames with black (24fps, 720p) – prompt the model: 'fill
-
Experimentation with Hyperframes and Gemini agent flow for annotated videos
By
–
I'm messing around with an agent flow for combining Hyperframes with Gemini video analysis to make interesting annotated videos. pic.twitter.com/hmoGqwopqI
— fofr (@fofrAI) 12 juin 2026I'm having fun experimenting with an agent flow to combine Hyperframes with Gemini's video analysis to create interesting annotated videos.
-
Progress in fine-grained 3D motion control for AI video
By
–
Fine-grained 3D motion control in AI video just got a little bit closer https://t.co/Uqi4lVJunR
— fofr (@fofrAI) 12 juin 2026Fine-grained 3D motion control in AI-generated video just got a little closer
-
Techniques for randomness and diversity in language model outputs
By
–
Summary of things: – turn up randomness and ban the most likely words (temperature + min-p + XTC sampling)
– ask for several different options at once, seed each with random constraints (verbalized sampling + entropy injection)
– give it a memory of what it's said and pick the -
Experimentation with Gemma 4 for creative fashion prompts
By
–
I experimented with using modifications of Gemma 4 to create creative prompts repeatedly. There are still a few quirks, but these are all results from the same simple query: "a dynamic fashion photo of a woman".
-
Google Diffusion Gemma and visual guide for faster text generation
By
–
Blog post: https://
blog.google/innovation-and
-ai/technology/developers-tools/diffusion-gemma-faster-text-generation/
… And a good visual guide to how it works by @MaartenGr
: https://
newsletter.maartengrootendorst.com/p/a-visual-gui
de-to-diffusiongemma
… -
DiffusionGemma: simultaneous word selection, 4x faster
By
–
DiffusionGemma, where the LLM picks words all at once. Which is 4x faster.
— fofr (@fofrAI) 10 juin 2026
You can get started with the weights and instructions here:https://t.co/YuChVfUMIU
pic.twitter.com/QJAWdWzmHyDiffusionGemma, where the LLM selects all words at once. Which is 4x faster. You can start with the weights and instructions here: