Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

experimenting with realtime latent consistency models in Figma

Jordan Singer

181,199 subscribers

374,763 views • 3 years ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Jordan Singer3 years ago

via @fal_ai_data before and after

Jordan Singer2 years ago

just open-sourced this:

Courtney Guertin3 years ago

@figma @figma is so lucky to have you. What an incredible combo

Shirley Miao3 years ago

@figma Holy crap

Sonny3 years ago

@figma reminds me to your demo @lichinlin in @tldraw 🤯

Clayton Farr3 years ago

@figma Jordan, manipulating LCMs with Figma control is 🤌 Thanks for always experimenting with these, and sharing repos when possible

Namya @ Supafast3 years ago

@figma noo wayyy 🤯

Mickey Friedman3 years ago

@figma fast shipping 👏

Greg Huntoon3 years ago

@figma Oh no, you’re taking my job. I make palm tree art. Damn. Fun while it lasted.

Collin Hadley3 years ago

@figma Holy fuck

Related Videos

🎨 new technologies necessitate new interfaces with real-time latent consistency models, here’s a different kind of drawing app:

🎨 new technologies necessitate new interfaces with real-time latent consistency models, here’s a different kind of drawing app:

Jordan Singer

1,470,934 views • 2 years ago

- Generate assets with prompts in Midjourney - Remove backgrounds in Figma - Adjust colors for consistency - Save days of work

- Generate assets with prompts in Midjourney - Remove backgrounds in Figma - Adjust colors for consistency - Save days of work

Emy

148,534 views • 2 years ago

Latent mask inpainting with H3 enables highly divergent changes while holding consistency. Examples by PhoenixRisen + AbleJones - workflow below.

Latent mask inpainting with H3 enables highly divergent changes while holding consistency. Examples by PhoenixRisen + AbleJones - workflow below.

Banodoco

11,019 views • 2 months ago

Experimenting with the new SDF nodes in Geometry Nodes. 30k particles colliding with a complex scene in realtime. The scene is baked into SDF grid. Blender 4.5 #blender #b3d #geometrynodes

Experimenting with the new SDF nodes in Geometry Nodes. 30k particles colliding with a complex scene in realtime. The scene is baked into SDF grid. Blender 4.5 #blender #b3d #geometrynodes

Shahzod Boyhonov

64,787 views • 1 year ago

This is fully realtime — not sped up. I’ve been experimenting with Realtime-2 and trying to move beyond “turn-for-turn” conversations. No toggling Whisper. Just endlessly talking into the terminal. Paired with Codex Spark, the immediate feedback starts to feel pretty magical. By EOY, I imagine we’ll be doing this with top-tier models.

This is fully realtime — not sped up. I’ve been experimenting with Realtime-2 and trying to move beyond “turn-for-turn” conversations. No toggling Whisper. Just endlessly talking into the terminal. Paired with Codex Spark, the immediate feedback starts to feel pretty magical. By EOY, I imagine we’ll be doing this with top-tier models.

Jaytel

110,432 views • 5 months ago

Introducing AI Canvas with LoRAs 🎨 Upload any LoRAs for character/style consistency on our Realtime AI Canvas. Create anime art with your favorite characters, in real-time.

Introducing AI Canvas with LoRAs 🎨 Upload any LoRAs for character/style consistency on our Realtime AI Canvas. Create anime art with your favorite characters, in real-time.

AI Waifus

2,093,096 views • 2 years ago

Hands-on Hallucination session: Focusing the diffusion process with the Hallucination Scope.⁣ Experimenting with new ways to explore and transform a scene.⁣ ⁣ #AI #StableDiffusion #Realtime

Hands-on Hallucination session: Focusing the diffusion process with the Hallucination Scope.⁣ Experimenting with new ways to explore and transform a scene.⁣ ⁣ #AI #StableDiffusion #Realtime

Hugues Bruyère

15,408 views • 1 year ago

One of the very interesting challenges with AI models for robotics is the constraints you're working with when deploying models that need to run in realtime on-device.

One of the very interesting challenges with AI models for robotics is the constraints you're working with when deploying models that need to run in realtime on-device.

AI at Meta

47,429 views • 1 year ago

Latent Spatial Memory for Video World Models

Latent Spatial Memory for Video World Models

AK

22,856 views • 5 months ago

Made in Figma, in collaboration with some of our friends

Made in Figma, in collaboration with some of our friends

Figma

134,806 views • 5 months ago

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...

Jesse Engel

183,911 views • 1 year ago

Updates to the Figma MCP server: → Generate and edit decks in Figma Slides → Build boards with data in FigJam → Roundtrip from code to canvas in Figma Make Now with custom font support and image exports.

Updates to the Figma MCP server: → Generate and edit decks in Figma Slides → Build boards with data in FigJam → Roundtrip from code to canvas in Figma Make Now with custom font support and image exports.

Figma

97,103 views • 4 months ago

Map2World. turns text descriptions and sketch maps into full 3D worlds. -multi-diffusion in SLAT latent space for global consistency; - beaats SynCity - supports arbitrary world sizes.

Map2World. turns text descriptions and sketch maps into full 3D worlds. -multi-diffusion in SLAT latent space for global consistency; - beaats SynCity - supports arbitrary world sizes.

Wildminder

15,679 views • 6 months ago

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

AK

82,138 views • 3 years ago

The new Realtime API with web crawling is mind-blowing! Talk in realtime with any website. Powered by the OpenAI Realtime API and 🔥 Check it out:

The new Realtime API with web crawling is mind-blowing! Talk in realtime with any website. Powered by the OpenAI Realtime API and 🔥 Check it out:

Nicolas Camara

347,277 views • 2 years ago

Fully realtime 3D inflation shader in Figma. Pretty hyped about this one! Need to polish it up and make the UI a bit easier to use but will share in a couple of days. Soooo much fun to play with!

Fully realtime 3D inflation shader in Figma. Pretty hyped about this one! Need to polish it up and make the UI a bit easier to use but will share in a couple of days. Soooo much fun to play with!

Piers Cowburn

16,901 views • 4 months ago

Back at it again: ways to make your life easier with JavaScript in Figma

Back at it again: ways to make your life easier with JavaScript in Figma

Figma

56,241 views • 1 year ago

We just acquired @weavy_ai, soon to be known as Figma Weave. With Weavy, you’ll get more models, more tools, more ways to create within the canvas. More to come

We just acquired @weavy_ai, soon to be known as Figma Weave. With Weavy, you’ll get more models, more tools, more ways to create within the canvas. More to come

Figma

949,633 views • 1 year ago

Figma Motion in Figma Motion

Figma Motion in Figma Motion

Figma

78,302 views • 4 months ago

experimenting with apple's spatial thingy in

experimenting with apple's spatial thingy in

Pablo Stanley

42,247 views • 10 months ago