Trained for 4 epochs and 70 steps.

Trained with datasets ['alt-embed-cache', 'cheechandchong-1024']
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: HiDream-ai/HiDream-I1-Full
VAE: HiDream-ai/HiDream-I1-Full

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6124e5cf71e5b4e13bb4d55a110c80d30df570017c984c21b51133ded8caf7de
+oid sha256:9ba229579c2b57c8bc19e74006f13996bd02f88c8979b600e79f40b1ffeaaa6d
 size 8689144