uisato

Oscilloscopes, Eveywhere [v1.2] is a collection of all the experiments with sound and geometry I've made throughout the years, gathered into one TouchDesigner project. This walkthrough explores the entire anthology in real-time; 29 presets, and a much more intuitive interface. Connect your audio sou

A novel way to intervene existing video through diffusion, particularly abstract visuals [in this case, audio-reactive geometries]: taking its movement and form as the starting point, and reinterpreting its textures, materials, and visual language. I’ve been developing this around the audio-reactive

perceptual_display_engine / experiment nº3 vfx / system design / soundscape: myself For this piece, I wanted to explore continuous motion across different AI-generated shots, later recomposed through my Perceptual Display Engine patch for TouchDesigner. The workflow: I first generated a “main” refer

It’s an experimental multi-source video player designed for frame-accurate video switching, playback manipulation, and display/render interventions. You can load multiple videos, decide exactly how many frames each source appears for, control how each source’s playhead behaves, insert black frames,

A few experiments made with Uisato Studio’s Seedance 2 "intelligent" implementation, exploring how far generative video + fine-tuned orchestration layers can be pushed in rhythm, camera language, body transformation, and audiovisual sync. Treating AI as a new choreographic tool beyond the limits of

motion_ctrl / experiment nº3 choreography: Sara Silkin dancers: Coco Williams & Joey Vice vfx: myself In collaboration with Sara, Joey, and Coco, I transformed a low-resolution recording of this beautiful performance, into this multi-angle audiovisual piece. Want the exact breakdown of how this was

The new ecosystem for AI orchestrated filmmaking + avant-garde tools for creators. A full year of the heaviest experimentation I’ve ever put myself through, now avaialble. https://uisato.studio/

New patch update is live on Patreon's shop post! This version adds VEO 3.1 support to the generator, plus the ability to generate with both start frame + last frame directly inside the patch. It also introduces resolution selection (720p, 1080p, 4k), improved model selection between VEO 2 and VEO 3.

I came accross this viral video in which an expensive After Effects plugin was used [Twixtor]. After a few tries, I was able to replicate results using TouchDesigner and Flowframes. Enjoy! Realtime Audioreactive Time Remap - [TouchDesigner's Twixtor Plugin Clone - Free Project Files] (YouTube)

New orchestration engine [WIP] Here, a preview of one of its modes: "music-video". Input: image [artist] + audio track Output: a modest video clip. Around 12 minutes of generation time / multi-GPU [H100s]. Hopefully, this will be all out soon. In the meantime, I'd love to read you: what is it that y

A complex AI live-style performance introducing with Camille. In her performance, gestures control harmony; AI lip/hand transfer aligns the avatar to the music. I recorded the performance from multiple angles and mapped lips + hand cues in an attempt to push “AI musical avatars” beyond just lip-sync

Full video here. Tools used: Google's VEO 3 [video generation] Google's Gemini [lyrics + prompt generation/refinement] Ableton Live [audio backing track generation] UDIO [audio backing track embelishment + mastering] Adobe Premiere [editing, golor grading] Time spent: Approximately 5 days This inclu

Enjoy! ♥ maxresdefault.jpg (YouTube)

Thank you everyone for participating, and congratulations to the winner! See you next time ♥ maxresdefault.jpg (YouTube)

More examples in: https://www.youtube.com/shorts/G2Rl8-ijSJw Just like the last two contest: - “ଧନ” patrons get 3 (three) chances to get this project file. - “ୡ୭ ફ” get 2 (two) chances. - “୬୯” patrons get 1 (one) chance. I’ll make a randomizer the 31th of November and whoever comes up, voilà: gets a