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 peak memory issue with H3. (#15486)
comfyanonymous62b3c94bd451
diff --git a/comfy/ldm/minimax/model.py b/comfy/ldm/minimax/model.pyindex 76174483a..f745db884 100644--- a/comfy/ldm/minimax/model.py+++ b/comfy/ldm/minimax/model.py@@ -165,6 +165,7 @@ class Attention(nn.Module):else:q = self.q_norm(q.view(s, self.heads, self.head_dim))k = self.k_norm(k.view(s, self.heads, self.head_dim))+ v = v.clone()q = AttentionTensorContainer(q.transpose(0, 1).unsqueeze(0))k = AttentionTensorContainer(k.transpose(0, 1).unsqueeze(0))v = AttentionTensorContainer(v.transpose(0, 1).unsqueeze(0))