- Fun with famous IP:
- Vectors: StarVector: Generating Scalable Vector Graphics Code from Images
- How to train a custom Stable Diffusion model to generate consistent characters via LensGo.ai, which lets you train 3 custom models for free every month.
- Insane 128x zoom-in on AI-generated meat.
Monthly Archives: December 2023
AI Holiday Leftovers, Vol. 2
- 3D:
- Paint Anything 3D with Lighting-Less Texture Diffusion Models: “Paint3D is a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs.”
- “Google just revealed an ABSOLUTE depth estimation model. As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image.”
- Typography:
- Retro-futuristic alphabet rendered with Midjourney V6: “Just swapped out the letter and kept everything else the same. Prompt: Letter “A”, cyberpunk style, metal, retro-futuristic, star wars, intrinsic details, plain black background. Just change the letter only. Not all renders are perfect, some I had to do a few times to get a good match. Try this strategy for any type of cool alphabet!”
- As many others have noted, Midjourney is now good at type. Find more here.
AI Holiday Leftovers, Vol. 1
Dig in, friends. 🙂
- Drawing/painting:
- Using a simple kids’ drawing tablet to create art: “I used @Vizcom_ai to transform the initial sketch. This tool has gotten soo good by now. I then used @LeonardoAi_’s image to image to enhance the initial image a bit, and then used their new motion feature to make it move. I also used @Magnific_AI to add additional details to a few of the images and Decohere AI’s video feature.”
- Latte art: “Photoshop paint sent to @freepik’s live canvas. The first few seconds of the video are real-time to show you how responsive it is. The music was made with @suno_ai_. Animation with Runways Gen-2.”
- Photo editing:
- Google Photos gets a generative upgrade: “Magic Eraser now uses gen AI to fill in detail when users remove unwanted objects from photos. Google Research worked on the MaskGIT generative image transformer for inpainting, and improved segmentation to include shadows and objects attached to people.”
- Clothing/try-on:
- PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns: “We propose a novel virtual try-on from unconstrained designs (ucVTON) task to enable photorealistic synthesis of personalized composite clothing on input human images.”
- AnyDoor is “a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations in a harmonious way.”
- SDXL Auto FaceSwap enables to create new images using the face of a source image (example attached).
AI: Tons of recent rad things
- 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.”
How-to: Combining Photoshop + ComfyUI
It’s a little nerdy even for my blood, but some of my teammates swear by these techniques that enable connecting Photoshop to a hosted instance of Stable Diffusion, enabling one to guide the process via a Photoshop doc and/or custom-trained styles:
“I Draw Better Than AI!”
Hah—I can dig this finger-rich pin from Pictoplasma.
To the moon! Insta360 makes a satellite
What if your tiny planet—a visual genre I’ve enjoyed beating halfway into the ground—were our actual planet? Insta360, on whom I’ve spent crazy amounts of money buying brilliant-if-maddening gear, has now sent their devices to the edge of space:
Catch up on great new Illustrator features in 60 seconds
Let’s talk vector generation, 3D mockup support, image-to-type, and more. Take ‘er away, Deke!
Promising 3D research from Adobe
Sam Altman on burnout vs. momentum
I find this almost searingly relatable.
AI image generation is getting *crazy* fast
Gemini is bonkers
I mean, seriously, what even is all this?? I can’t explain; just please watch.
- 0:00 Intro
- 0:19 Multimodal Dialogue
- 1:32 Multilinguality 2:04
- Game Creation 2:31
- Visual Puzzles 3:17
- Making Connections
- 3:39 Image & Text Generation
- 4:06 Logic & Spatial Reasoning
- 4:55 Translating Visuals
- 5:27 Cultural Understanding
Baby, You Can Drive My Bricks
I’ve had way too much fun creating custom Lego sets based on friends’ & family’s rides, so to help others do it, I’ve made my first custom GPT, “Baby You Can Drive My Bricks.” Take it for a spin & let me know what you create!
