quzo commited on
Commit
db6bae6
·
verified ·
1 Parent(s): ec5fb3a

Trained for 35 epochs and 900 steps.

Browse files

Trained with datasets ['text-embeds', 'bartek-mizak-flux']
Learning rate 0.0001, batch size 1, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: black-forest-labs/FLUX.1-dev
VAE: None

Files changed (1) hide show
  1. pytorch_lora_weights.safetensors +1 -1
pytorch_lora_weights.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:105e77265a94b7ed55c14aef84cd452086a2148e37b35142f2a31b7270264e6a
3
  size 109535132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afded361292170d8629553791c3f6af6bc4bd518f0dd2de273f98d1b3a5b6ca2
3
  size 109535132