-
feed_forward_vqgan_clip
Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
WOMBO I suspect uses the feed forward inferential approach to VQGAN + CLIP (instead of finetuning, predict the final z latent vector for a given text input) which is why their outputs are less sophisticated: as a result there are many deployment optimizations you can do to speed that up, which may be complicated.
NOTE:
The number of mentions on this list indicates mentions on common posts plus user suggested alternatives.
Hence, a higher number means a more popular project.
Related posts
-
A small experiment on how changes in a text prompt may affect output image in a CLIP-based system
-
Get a VQGAN output image for a given text description almost instantly (not including time for one-time setup) using Colab notebook "Feed Forward VQGAN CLIP - Using a pretrained model" from mehdidc. Here are 20 non-cherry picked images from the notebook. Details in a comment.
-
MultiDiffusion Region Control, a prompt on each mask webui extension is out.
-
Hubble Diffusion with MultiDiffusion
-
MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation