text-to-image
MIT · Commercial use OK
text-to-image is a free, open-source alternative to DALL·E. It can be used without subscription fees — and its source code is open for anyone to inspect, modify and self-host.
License
MIT
Replaces
1 commercial tools
GitHub stars
⭐ 2.2k
Written in
Python
Forks
398
Last activity
8 years ago
Growth (7 days)
+1 ★
deep-learninggenerative-adversarial-networkskip-thought-vectorstensorflow
About
Text to image synthesis using thought vectors Its license (MIT) is permissive: free to use, modify and redistribute — including inside commercial and proprietary products.
What switching gets you
- No subscription, no per-seat pricing — free forever, for individuals and companies alike.
- Your data stays with you: it can run locally or on your own servers, with no vendor lock-in.
- The source code is public — auditable, extensible and maintained in the open by its community.
An open-source alternative to
Other alternatives worth a look
mmagicOpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.DALLE2-pytorchImplementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in PytorchSanaSANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerimagen-pytorchImplementation of Imagen, Google's Text-to-Image Neural Network, in Pytorchcustom-diffusionCustom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)HunyuanImage-2.1HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation