#ProjectScribbler
summary
An interactive deep‑learning image generator that colorizes and completes sketches using Adobe Sensei, trained on tens of thousands of photos to recognize facial features and plausible colors. Users sketch shapes, drop swatches and drag-and-drop textures as hints; the model performs texture propagation and fills color across the sketch in real time. Demos include portrait colorization and character-plus-handbag designs exported to Photoshop; occasional wrong skin‑tone guesses occur and manual color controls are listed as a forthcoming fix.
AI-written summary · about
related talks
19mSketchforme: Composing Sketched Scenes from Text Descriptions for Interactive Applications
01h 27mImage Generation with AI
11mAI-powered JavaScript applications
40mSketch-n-Sketch: Interactive SVG Programming with Direct Manipulation
32mSelf-Portraits in JavaScript
56mPicasso's terminal; data science and AI in the visual arts
13m[Interactive] Neural Style Transfer: The Art and Science of Generative AI
19mA Mixed-Initiative Interface for Animating Static Pictures