Pinkstack commited on
Commit
81d4601
·
verified ·
1 Parent(s): 2b6871f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -80,6 +80,7 @@ image.save("LiliPixel-image.png")
80
  - LiliPixel has been trained on a limited amount of pictures and it has a limited parameter size, do not expect the model to generate complex scenes or niche objects/places, for example instead of prompting "Blahaj" prompt "Cute light blue colored shark plushy".
81
  - In 64x64 mode, the model has a higher chance of hallucinating subjects. Ideally bulk-generate 8-16 images at once and select the best looking image.
82
  - As the model is small, ideally generate multiple images with the same prompt across different seeds and select the best looking image, as the model is small generating images on GPU or even CPU should be near-instant.
 
83
 
84
  ## Training
85
 
 
80
  - LiliPixel has been trained on a limited amount of pictures and it has a limited parameter size, do not expect the model to generate complex scenes or niche objects/places, for example instead of prompting "Blahaj" prompt "Cute light blue colored shark plushy".
81
  - In 64x64 mode, the model has a higher chance of hallucinating subjects. Ideally bulk-generate 8-16 images at once and select the best looking image.
82
  - As the model is small, ideally generate multiple images with the same prompt across different seeds and select the best looking image, as the model is small generating images on GPU or even CPU should be near-instant.
83
+ - at 16x16 more than 1 subject is complicated for the model, at 32x32 more than 3 subjects (eg; three berries) is complicated for the model. at 64x64 complex scenes may become incoherent and inconsistent.
84
 
85
  ## Training
86