Trained for 8 epochs and 100 steps.

Trained with datasets ['makima-text-embeds', 'makima-512']
Learning rate 0.0003, batch size 56, 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129080a20f73a5bf55cfd082a5b31a8b541f7a9475a7e63bcd522a02f41397a3
+size 418454776