Output of Craiyon (formerly "DALL-E Mini"). See the model card for information on the model used. Specifically (from the title card): "Images are encoded through a VQGAN encoder, which turns images into a sequence of tokens. Descriptions are encoded through a BART encoder. The output of the BART encoder and encoded images are fed through the BART decoder, which is an auto-regressive model whose goal is to predict the next token. Loss is the softmax cross-entropy between the model prediction logits and the actual image encodings from the VQGAN." Upscaled using Real-ESRGAN.
This file is in the public domain because it is the work of a computer algorithm or artificial intelligence and does not contain sufficient human authorship to support a copyright claim.
The United Kingdom and Hong Kong provide a limited term of copyright protection for computer-generated works of 50 years from creation. [1][2]
File history
Click on a date/time to view the file as it appeared at that time.