simonsanvil/DALL-E-Explained
Description and applications of OpenAI's paper about DALL-E (2021) and implementation of other (CLIP-guided) zero-shot text-to-image generation schemes
Generate unique images from text descriptions without needing extensive training data for each new concept. You input a text prompt describing an image, and the system creates a corresponding visual output. This tool is for artists, designers, marketers, or anyone needing custom visual content quickly from simple text instructions.
No commits in the last 6 months.
Use this if you need to rapidly create diverse images from textual ideas, like visualizing a product concept or generating creative art.
Not ideal if you require pixel-perfect control over every detail of the generated image or need to work with a fixed set of predefined image categories.
Stars
33
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 11, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/simonsanvil/DALL-E-Explained"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai-forever/ru-dalle
Generate images from texts. In Russian
KR-HappyFace/KoDALLE
🇰🇷 Text to Image in Korean
j-min/DallEval
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)
olaviinha/NeuralTextToImage
Colabs for text prompt steered image generators
kevinhermawan/Canvas
DALL·E playground for the Mac