CLIP: Connecting text and images - OpenAI
Jan 5, 2021 · We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GPT-2 and GPT-3.
Multimodal neurons in artificial neural networks - OpenAI
Mar 4, 2021 · Within CLIP, we discover high-level concepts that span a large subset of the human visual lexicon—geographical regions, facial expressions, religious iconography, famous people and more. By probing what each neuron affects downstream, we can get a glimpse into how CLIP performs its classification.
Hierarchical text-conditional image generation with CLIP latents
Apr 13, 2022 · To leverage these representations for image generation, we propose a two-stage model: a prior that generates a CLIP image embedding given a text caption, and a decoder that generates an image conditioned on the image embedding.
ConVIRT trained from scratch, which we call CLIP, for Con-trastive Language-Image Pre-training, is an efficient method of learning from natural language supervision. We study the scalability of CLIP by training a series of eight models spanning almost 2 orders of magnitude of compute and ob-serve that transfer performance is a smoothly predictable
Research | OpenAI
Our research on generative modeling for images has led to representation models like CLIP, which makes a map between text and images that an AI can read, and DALL-E, a tool for creating vivid images from text descriptions.
GPT-4 - OpenAI
Research GPT-4 is the latest milestone in OpenAI’s effort in scaling up deep learning. View GPT-4 research Infrastructure GPT-4 was trained on Microsoft Azure AI supercomputers. Azure’s AI-optimized infrastructure also allows us to deliver GPT-4 to users around the world.
Sora | OpenAI
Feb 15, 2024 · Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt. Prompt: A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse.
DALL·E 2 - OpenAI
DALL·E 2 can take an image and create different variations of it inspired by the original. In January 2021, OpenAI introduced DALL·E. One year later, our newest system, DALL·E 2, generates more realistic and accurate images with 4x greater resolution.
OpenAI
Greater productivity. Endless inspiration. We believe our research will eventually lead to artificial general intelligence, a system that can solve human-level problems. Building safe and beneficial AGI is our mission.
DALL·E: Creating images from text - OpenAI
Jan 5, 2021 · DALL·E: Creating images from text. We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language. DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text–image pairs.
- Some results have been removed