metadata
license: mit
pipeline_tag: text-to-image
language:
- en
tags:
- image
- t2i
- text-to-image
- custom-code
- tiny
model-index:
- name: PixelModel-v2
results:
- task:
type: text-to-image
dataset:
name: fid
type: fid
metrics:
- name: fid
type: fid
value: 390.68
- task:
type: text-to-image
dataset:
name: clip
type: clip
metrics:
- name: clip
type: clip
value: 20.48
new_version: bench-labs/PixelModel-v3
See us on the Leaderboard ⇗ |
Blog post read it here ⇗ |
PixelModel v2 🖼️
A neural network where the weights are the image. Scaled up.
Consider looking at previous versions for more context.
23k parameters -> 200k parameters (thats the only change)
demo images
