Trained for 218 epochs and 1600 steps.

Trained with datasets ['alt-embed-cache', 'dreambooth-1024']
Learning rate 0.0001, batch size 1, and 1 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0837674f7263089b3a62cfc208ead73a9fd126c1db51c1f072316afdfeaaf79d
+size 23655824