diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py
index eaff12f0..372555ff 100644
--- a/modules/sd_hijack_optimizations.py
+++ b/modules/sd_hijack_optimizations.py
@@ -372,7 +372,7 @@ def scaled_dot_product_attention_forward(self, x, context=None, mask=None):
 
     dtype = q.dtype
     if shared.opts.upcast_attn:
-        q, k = q.float(), k.float()
+        q, k, v = q.float(), k.float(), v.float()
 
     # the output of sdp = (batch, num_heads, seq_len, head_dim)
     hidden_states = torch.nn.functional.scaled_dot_product_attention(