Trained for 72 epochs and 800 steps.
Browse filesTrained with datasets ['text-embeds', '2BoutOvalFlux1']
Learning rate 0.0001, batch size 6, 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
pytorch_lora_weights.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 359102760
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db7a58e6cd44aca12db2e7179250b758c18019aee310d664d5583c6bad722d96
|
3 |
size 359102760
|