15 days ago Use the provided reference image for the young man’s face and appearance. Keep his hairstyle, beard, and glasses the same. Transform the scene so that he is smiling confidently while holding Jerry, the playful cartoon mouse, gently in his arms. Behind him on the left, Tom the cartoon cat gives a big thumbs-up with an excited expression. The background should be a cozy interior with cinematic lighting, a glowing chandelier, and soft ambient light. Blend live-action and 3D animation in a hyper-rea, GPTHIVE 1 46
5 months ago A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection. The text reads: (left) "Transfer between Modalities: Suppose we directly model p(text, pixels, sound) [equation] with one big autoregressive transformer. Pros: * image generation augmented with vast world knowledge * next-level text rendering * native in-context learning * unified post-training stack Cons: * varying bit-rate across modalities * compute not adaptive" (Right) "Fixes: * model compressed representations * compose autoregressive prior with a powerful decoder" On the bottom right of the board, she draws a diagram: "tokens -> [transformer] -> [diffusion] -> pixels" alexsdai PRO 1 140