AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-10-23 09:09:01 +03:00
Code Activity

Fix AuraFlow attn processors applying norm_added_q to key projection (#13533)

Browse Source 
Both AuraFlowAttnProcessor2_0 and FusedAuraFlowAttnProcessor2_0 were
calling attn.norm_added_q on encoder_hidden_states_key_proj while
guarded by a check on attn.norm_added_k. This applies the query
normalization layer to the key, which is a copy-paste error.

Consistent with every other attention processor in this file that
defines both norm_added_q and norm_added_k (e.g. FluxAttnProcessor,
CogVideoXAttnProcessor, HunyuanAttnProcessor), where norm_added_k is
applied to the added key projection.
This commit is contained in:
Ricardo-M-L
2026-04-22 03:20:54 +08:00
committed by GitHub
parent 3d30b7d9d2
commit b9d6420447
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/diffusers/models/attention_processor.py
View File

@@ -2140,7 +2140,7 @@ class AuraFlowAttnProcessor2_0:
if attn.norm_added_q is not None:
encoder_hidden_states_query_proj = attn.norm_added_q(encoder_hidden_states_query_proj)
if attn.norm_added_k is not None:
encoder_hidden_states_key_proj = attn.norm_added_q(encoder_hidden_states_key_proj)
encoder_hidden_states_key_proj = attn.norm_added_k(encoder_hidden_states_key_proj)
query = torch.cat([encoder_hidden_states_query_proj, query], dim=1)
key = torch.cat([encoder_hidden_states_key_proj, key], dim=1)
@@ -2237,7 +2237,7 @@ class FusedAuraFlowAttnProcessor2_0:
if attn.norm_added_q is not None:
encoder_hidden_states_query_proj = attn.norm_added_q(encoder_hidden_states_query_proj)
if attn.norm_added_k is not None:
encoder_hidden_states_key_proj = attn.norm_added_q(encoder_hidden_states_key_proj)
encoder_hidden_states_key_proj = attn.norm_added_k(encoder_hidden_states_key_proj)
query = torch.cat([encoder_hidden_states_query_proj, query], dim=1)
key = torch.cat([encoder_hidden_states_key_proj, key], dim=1)