Trained for 1 epochs and 10 steps.

Trained with datasets ['text-embed-cache', 'edited-images-768']
Learning rate 5e-05, batch size 1, and 1 gradient accumulation steps.
Trained with None prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: Shitao/OmniGen-v1-diffusers
VAE: Shitao/OmniGen-v1-diffusers

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ca6b5caf90f721853cc399cdecf4cc29fdf5463c77b0228aa7ed35ce6cde0f
+oid sha256:af859cd045453e80a7de23b35f3a1bac1bf8401f64546c27147df9d5bca40948
 size 4383592