{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2021-01-05-dall-e-clip/","md":"https://postcutoff.com/e/2021-01-05-dall-e-clip/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2021-01-05-dall-e-clip","date":"2021-01-05","date_precision":"day","short_title":"OpenAI unveils DALL·E and CLIP","deck":null,"takeaway":"DALL·E generated images from text prompts using a 12B-parameter Transformer, and CLIP learned joint image–text representations from 400M image-caption pairs; CLIP became a key component of later diffusion image generators.","category":"media-generation","category_label":"Media generation","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"DALL·E: Creating images from text (OpenAI)","url":"https://openai.com/index/dall-e/","type":"official","group":"primary","domain":"openai.com"},{"n":2,"title":"CLIP: Connecting text and images (OpenAI)","url":"https://openai.com/index/clip/","type":"official","group":"primary","domain":"openai.com"},{"n":3,"title":"Learning Transferable Visual Models From Natural Language Supervision (arXiv)","url":"https://arxiv.org/abs/2103.00020","type":"paper","group":"primary","domain":"arxiv.org"},{"n":4,"title":"Zero-Shot Text-to-Image Generation (arXiv)","url":"https://arxiv.org/abs/2102.12092","type":"paper","group":"primary","domain":"arxiv.org"}],"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["OpenAI"],"title":"OpenAI unveils DALL·E and CLIP","summary":"DALL·E generated images from text prompts using a 12B-parameter Transformer, and CLIP learned joint image–text representations from 400M image-caption pairs; CLIP became a key component of later diffusion image generators.","key_facts":["Both announced 5 January 2021","DALL·E: 12-billion-parameter version of GPT-3 trained on text–image pairs","CLIP: trained on 400M image–text pairs; strong zero-shot ImageNet accuracy","CLIP weights open-sourced; used by Stable Diffusion's text encoder (v1)"],"key_numbers":[],"tags":["text-to-image","multimodal","contrastive-learning"],"science":null,"body_md":"## What happened\n\nOpenAI introduced a text-to-image model and a contrastive vision-language model on the same day.\n\n## Why it matters\n\nLaunched the text-to-image era and made natural language the interface for vision models.","disputed":[],"related":[{"id":"2022-08-22-stable-diffusion","url":"https://postcutoff.com/e/2022-08-22-stable-diffusion/","date":"2022-08-22","date_precision":"day","short_title":"Stable Diffusion released as open weights","deck":null,"takeaway":"The open-weights release made generative AI a grassroots movement and set off legal battles over training data.","category":"open-source","category_label":"Open source","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Stability AI","CompVis (LMU Munich)","Runway"]},{"id":"2022-04-06-dall-e-2","url":"https://postcutoff.com/e/2022-04-06-dall-e-2/","date":"2022-04-06","date_precision":"day","short_title":"DALL·E 2 brings photorealistic text-to-image generation","deck":null,"takeaway":"Marked diffusion models' takeover of image generation and triggered debates on artists' rights and synthetic media.","category":"media-generation","category_label":"Media generation","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["OpenAI"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/openai-dall-e-clip"}