Trained for 33 epochs and 12700 steps.

Trained with datasets ['text-embeds', 'q1sV15-1024-crop', 'q1sV15-512-crop', 'pseudo-camera-10k-flux-1024-reg']
Learning rate 0.0001, batch size 1, and 3 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:c598a1f1edd1956ddee4c4b2e557041133620501ca83cff2483f451de7025c85
+oid sha256:77b641783077e3acbbe902cfc8eec9ea79b45c21990cf8f25b9129e631af7944
 size 109535132