Update train_text_to_image_sdxl.py (#8830)

jiagaoxiang · linoytsaban · web-flow · commit f7822ae4bf65 · 2025-01-02T10:41:18.000-10:00
Enable VAE hash to be able to change with args change. If not, train_dataset_with_embeddiings may have row number inconsistency with train_dataset_with_vae.

Co-authored-by: Linoy Tsaban &lt;57615435+linoytsaban@users.noreply.github.com&gt;
diff --git a/examples/text_to_image/train_text_to_image_sdxl.py b/examples/text_to_image/train_text_to_image_sdxl.py
@@ -919,7 +919,7 @@ def preprocess_train(examples):
         # fingerprint used by the cache for the other processes to load the result
         # details: https://github.com/huggingface/diffusers/pull/4038#discussion_r1266078401
         new_fingerprint = Hasher.hash(args)
-        new_fingerprint_for_vae = Hasher.hash(vae_path)
+        new_fingerprint_for_vae = Hasher.hash((vae_path, args))
         train_dataset_with_embeddings = train_dataset.map(
             compute_embeddings_fn, batched=True, new_fingerprint=new_fingerprint
         )

Original file line number	Diff line number	Diff line change
`@@ -919,7 +919,7 @@ def preprocess_train(examples):`
`919`	`919`	`# fingerprint used by the cache for the other processes to load the result`
`920`	`920`	`# details: https://github.com/huggingface/diffusers/pull/4038#discussion_r1266078401`
`921`	`921`	`new_fingerprint = Hasher.hash(args)`
`922`		`- new_fingerprint_for_vae = Hasher.hash(vae_path)`
	`922`	`+ new_fingerprint_for_vae = Hasher.hash((vae_path, args))`
`923`	`923`	`train_dataset_with_embeddings = train_dataset.map(`
`924`	`924`	`compute_embeddings_fn, batched=True, new_fingerprint=new_fingerprint`
`925`	`925`	`)`