oops

README.md

@@ -21,11 +21,11 @@ WanGP supports the Wan (and derived models), Hunyuan Video and LTV Video models
 
 ## 🔥 Latest Updates
 ### July 8 2025: WanGP v6.6, WanGP offers you **Vace Multitalk Dual Voices Fusionix Infinite** :
-**Vace** our beloved super Control Net has been combined with **Multitalk** the new king in town that can animate two people speaking (**Dual Voices**). It is accelerated by the **Fusionix** model and thanks to *Sliding Windows* support and *Adaptive Projected Guidance* (much slower but should reduce the reddish effect with long videos) your two people will be able to talk for very a long time (which is an **Infinite** amount of time in the field of video generation).
+**Vace** our beloved super Control Net has been combined with **Multitalk** the new king in town that can animate up to two people speaking (**Dual Voices**). It is accelerated by the **Fusionix** model and thanks to *Sliding Windows* support and *Adaptive Projected Guidance* (much slower but should reduce the reddish effect with long videos) your two people will be able to talk for very a long time (which is an **Infinite** amount of time in the field of video generation).
 
 Of course you will get as well *Multitalk* vanilla and also *Multitalk 720p* as a bonus.
 
-And since I am mister nice guy I had enclosed as an exclusivity an *Audio Separator* that will save you time to isolate each voice when using Multitalk with two people.
+And since I am mister nice guy I have enclosed as an exclusivity an *Audio Separator* that will save you time to isolate each voice when using Multitalk with two people.
 
 As I feel like a resting a bit I haven't produced a nice sample Video to illustrate all these new capabilities. But here is the thing, I ams sure you will publish in the *Share Your Best Video* channel your *Master Pieces*. The best one will be added to the *Announcements Channel* and will bring eternal fame to its author.
 

wan/modules/attention.py

@@ -7,23 +7,23 @@ import torch.nn.functional as F
 major, minor = torch.cuda.get_device_capability(None)
 bfloat16_supported =  major >= 8 
 
-try:
+# try:
-    from xformers.ops import memory_efficient_attention
+#     from xformers.ops import memory_efficient_attention
-except ImportError:
+# except ImportError:
-    memory_efficient_attention = None
+#     memory_efficient_attention = None
 
-try:
+# try:
-    import flash_attn_interface
+#     import flash_attn_interface
-    FLASH_ATTN_3_AVAILABLE = True
+#     FLASH_ATTN_3_AVAILABLE = True
-except ModuleNotFoundError:
+# except ModuleNotFoundError:
-    FLASH_ATTN_3_AVAILABLE = False
+#     FLASH_ATTN_3_AVAILABLE = False
 
-try:
+# try:
-    import flash_attn
+#     import flash_attn
-    FLASH_ATTN_2_AVAILABLE = True
+#     FLASH_ATTN_2_AVAILABLE = True
-except ModuleNotFoundError:
+# except ModuleNotFoundError:
-    FLASH_ATTN_2_AVAILABLE = False
+#     FLASH_ATTN_2_AVAILABLE = False
-    flash_attn = None
+#     flash_attn = None
 
 try:
     from sageattention import sageattn_varlen

wan/multitalk/attention.py

@@ -5,19 +5,19 @@ from einops import rearrange, repeat
 from .multitalk_utils import RotaryPositionalEmbedding1D, normalize_and_scale, split_token_counts_and_frame_ids
 from wan.modules.attention import pay_attention
 
-import xformers.ops
+# import xformers.ops
 
-try:
+# try:
-    import flash_attn_interface
+#     import flash_attn_interface
-    FLASH_ATTN_3_AVAILABLE = True
+#     FLASH_ATTN_3_AVAILABLE = True
-except ModuleNotFoundError:
+# except ModuleNotFoundError:
-    FLASH_ATTN_3_AVAILABLE = False
+#     FLASH_ATTN_3_AVAILABLE = False
 
-try:
+# try:
-    import flash_attn
+#     import flash_attn
-    FLASH_ATTN_2_AVAILABLE = True
+#     FLASH_ATTN_2_AVAILABLE = True
-except ModuleNotFoundError:
+# except ModuleNotFoundError:
-    FLASH_ATTN_2_AVAILABLE = False
+#     FLASH_ATTN_2_AVAILABLE = False
 
 import warnings