Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
bghira
/
pseudo-journey-v2
like
11
Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
Inference Endpoints
License:
creativeml-openrail-m
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
main
pseudo-journey-v2
3 contributors
History:
8 commits
ptx0
Update scheduler config for diffusers for trailing timestep
0064e7f
about 1 year ago
feature_extractor
13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data)
over 1 year ago
scheduler
Update scheduler config for diffusers for trailing timestep
about 1 year ago
text_encoder
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
about 1 year ago
tokenizer
13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data)
over 1 year ago
unet
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
about 1 year ago
vae
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
about 1 year ago
.gitattributes
1.48 kB
initial commit
over 1 year ago
README.md
1.84 kB
Update README.md
about 1 year ago
config.yaml
1.81 kB
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
about 1 year ago
model_index.json
543 Bytes
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
about 1 year ago