- Realtime:
- Oh look, I’m George Clooney! Kinda. You can be, too. FAL AI promises “AI inference faster than you can type.”
- “100ms image generation at 1024×1024. Announcing Segmind-Vega and Segmind-VegaRT, the fastest and smallest, open source models for image generation at the highest resolution.”
- Krea has announced their open beta, “free for everyone.”
- How incredible would it be to have realtime generative brushes like this?
- Drawing to Video, made using Vizcom -> Leonardo -> Pika.
- 3D generation:
- ByteDance has released ImageDream (image to 3D)
- SceneWiz3D offers “A new approach to create high-fidelity 3D scenes from text and 3D object control”
- Image -> depth -> geometry using Marigold + Blender
- 3D for fashion, sculpting, and more:
- This is what Adobe Substance & a notional 3D mode of Firefly Text-to-Image should feel like.
- Outfit Anyone + Animate Anyone = virtual try on + movement.
- Sculpting/rendering via Adobe Substance 3D Modeler + Dreams + Unbound + Krea.
- AnimateDiff v3 was just released.
- Instagram has enabled image generation inside chat (pretty “meh,” in my experience so far), and in stories creation, “It allows you to replace a background of an image into whatever AI generated image you’d like.”
- “Did you know that you can train an AI Art model and get paid every time someone uses it? That’s Generaitiv’s Model Royalties System for you.”
Best posting day ever John!!! SO much amazing stuff. We all appreciate you keeping us up to date even if we only understand 50% of it.
Hah—thanks, Clay! Lots more where this came from. 🙂