Machine Telephone ☎️
Enter a concept. 'Dial a machine' to pass information across different modalities and see how context shifts or evolves as it's interpreted sequentially.
📢 New @heyjasper release ! 📢
MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image research.
Nano T2I 🖌️ : A codebase to train your own T2I model
🤗 @huggingface: https://t.co/x6gEhQIaFV
💻: https://t.co/K6VIU2wjtW
Very excited about this new release, pushing the boundaries of open and reproducible T2I research.
Congrats to the team!
Benjamin Aubin Gonzalo Quintana @onurxtasar@UlaLaParis@_jeev2@dh7net@clipdropapp@heyjasperai
📢 New @heyjasper release ! 📢
MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image research.
Nano T2I 🖌️ : A codebase to train your own T2I model
🤗 @huggingface: https://t.co/x6gEhQIaFV
💻: https://t.co/K6VIU2wjtW
Very excited about this new release, pushing the boundaries of open and reproducible T2I research.
Congrats to the team!
Benjamin Aubin Gonzalo Quintana @onurxtasar@UlaLaParis@_jeev2@dh7net@clipdropapp@heyjasperai
We knew very little about how LLMs actually work...until now.
@AnthropicAI just dropped the most insane research paper, detailing some of the ways AI "thinks."
And it's completely different than we thought.
Here are their wild findings: 🧵
Excited to share our new research at @heyjasperai !🚀
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
Try out our @huggingface space for object relighting!
🤗@Gradio demo: https://t.co/wXKrssU3BB
👉Paper: https://t.co/YKAu9G9pdv
💻Repo: https://t.co/Ghft5J34vC
Presenting ShaderGPT™, an AI experiment.
Which LLM is best at coding visual GLSL fragment shaders?
OpenAI vs. DeepSeek vs. Mistral vs. Anthropic.
Write prompts and explore examples.
https://t.co/Mk9Dlt01zd
Built with AI SDK by @vercel.
🎉 Very happy to share that @heyjasperai's very first research paper, Flash Diffusion just got accepted to #AAAI.
This paper introduces a novel and flexible distillation method designed to speed up image generation with diffusion models.
👉 Paper: https://t.co/4NqzaWOkRL
the cube schematic & tvc4, edward zajec (1971)
tvc is less on design of visual modules, but of procedural ones. taken from "comp 3" organized by museo revoltella in trieste, italy in 1971. and one of the first exhibitions of digital art organized by a major museum at the time.
Realistic Water Simulation with #threejs is live:
https://t.co/XcmCC4hQnW
Now, you can configure scenes, objects, colors, and light positions. You can also dive to see the effects from underwater 🌊💧. It works great on mobile 🤩.
The breakdown video will be on my YouTube channel soon. Be sure to subscribe so you don't miss it: https://t.co/AZNU3lXhy4
Thanks again, Evan Wallace, for the inspiration 🙏🏻
#threejsjourney #creativecoding #r3f
I worked on a fun collaborative project with the writer Qiufan Chen called I Am Feeling Luckier, curated by the amazing Barbara Cueto�� and commissioned by the LAS Art Foundation. https://t.co/gZ7QUxzxmp (Works only on desktop with a webcam.)
i liked @basementstudio's https://t.co/QoquG0En2p so much i wanted to see how much effort it would be to create a shadow overlay. this is a quick throwaway using drei/softShadows (which DLC uses, too) and drei/scrollcontrols.
"After 34 Years, Someone Finally Beat Tetris"
Wow, incredible video on what it took to beat Tetris, waaay beyond the game's original design.
Also a great reference for reinforcement learning and what superintelligence might look like.
https://t.co/sNDzNlrTNV
🚀 Real-time image generation is now available on Clipdrop!
Test the beta version of SDXL Turbo now → https://t.co/u8LX8Lhgrt
Read more → https://t.co/0XUzizJqIS
@StabilityAI@StabilityAI_JP
Beautiful pixel artwork by Barbara Nessim in the September 1984 (Vol 9, No 10) issue of BYTE magazine. Drawn using Norpak videotex (NAPLPS) system, running on a PDP-11/03. This offered 6 drawing modes (arc, rectangle, circle, line, dot and polygon) and 12 colours + black & white.