Trained for 2 epochs and 4000 steps.

Trained with datasets ['text-embeds', 'dlay-images']
Learning rate 0.0001, batch size 2, and 2 gradient accumulation steps.
Trained with flow_matching prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: Qwen/Qwen-Image
VAE: Qwen/Qwen-Image

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82fbcfd9ba04bfe36963f091d534ef0354753d418c02a21620eb654b8a522cbf
-size 106799112
+oid sha256:fb943a860954032728bb05267a05db4ecf796578d1d16acd2142993809f33d1e
+size 106799048