Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Fix issue.

comfyanonymous33fb282d5c12
diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py
index 65a8bcf42..85ea406e0 100644
--- a/comfy/ldm/modules/attention.py
+++ b/comfy/ldm/modules/attention.py
@@ -358,7 +358,7 @@ def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_resh
disabled_xformers = True
if disabled_xformers:
- return attention_pytorch(q, k, v, heads, mask)
+ return attention_pytorch(q, k, v, heads, mask, skip_reshape=skip_reshape)
if skip_reshape:
q, k, v = map(