Trained for 49 epochs and 5500 steps.

Trained with datasets ['text-embed-cache', 'flux-dev-dataset-512', 'flux-dev-dataset-1024', 'flux-dev-dataset-512-crop', 'flux-dev-dataset-1024-crop']
Learning rate 0.001, batch size 4, 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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a4a7f091c48b17a9806a4bf108cdcbb7d715c9c50b2bc2d31c6a386511af39
+oid sha256:877d4a1b9831bd40967501650b6d2bc2f25e0c085b531505aae9ae676a3bf36e
 size 109535132