Fix issues with new hunyuan img2vid model and bumb version to v0.3.26

comfy/ldm/flux/layers.py

@@ -159,20 +159,20 @@ class DoubleStreamBlock(nn.Module):
         )
         self.flipped_img_txt = flipped_img_txt
 
-    def forward(self, img: Tensor, txt: Tensor, vec: Tensor, pe: Tensor, attn_mask=None, modulation_dims=None):
+    def forward(self, img: Tensor, txt: Tensor, vec: Tensor, pe: Tensor, attn_mask=None, modulation_dims_img=None, modulation_dims_txt=None):
         img_mod1, img_mod2 = self.img_mod(vec)
         txt_mod1, txt_mod2 = self.txt_mod(vec)
 
         # prepare image for attention
         img_modulated = self.img_norm1(img)
-        img_modulated = apply_mod(img_modulated, (1 + img_mod1.scale), img_mod1.shift, modulation_dims)
+        img_modulated = apply_mod(img_modulated, (1 + img_mod1.scale), img_mod1.shift, modulation_dims_img)
         img_qkv = self.img_attn.qkv(img_modulated)
         img_q, img_k, img_v = img_qkv.view(img_qkv.shape[0], img_qkv.shape[1], 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)
         img_q, img_k = self.img_attn.norm(img_q, img_k, img_v)
 
         # prepare txt for attention
         txt_modulated = self.txt_norm1(txt)
-        txt_modulated = apply_mod(txt_modulated, (1 + txt_mod1.scale), txt_mod1.shift, modulation_dims)
+        txt_modulated = apply_mod(txt_modulated, (1 + txt_mod1.scale), txt_mod1.shift, modulation_dims_txt)
         txt_qkv = self.txt_attn.qkv(txt_modulated)
         txt_q, txt_k, txt_v = txt_qkv.view(txt_qkv.shape[0], txt_qkv.shape[1], 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)
         txt_q, txt_k = self.txt_attn.norm(txt_q, txt_k, txt_v)
@@ -195,12 +195,12 @@ class DoubleStreamBlock(nn.Module):
             txt_attn, img_attn = attn[:, : txt.shape[1]], attn[:, txt.shape[1]:]
 
         # calculate the img bloks
-        img = img + apply_mod(self.img_attn.proj(img_attn), img_mod1.gate, None, modulation_dims)
-        img = img + apply_mod(self.img_mlp(apply_mod(self.img_norm2(img), (1 + img_mod2.scale), img_mod2.shift, modulation_dims)), img_mod2.gate, None, modulation_dims)
+        img = img + apply_mod(self.img_attn.proj(img_attn), img_mod1.gate, None, modulation_dims_img)
+        img = img + apply_mod(self.img_mlp(apply_mod(self.img_norm2(img), (1 + img_mod2.scale), img_mod2.shift, modulation_dims_img)), img_mod2.gate, None, modulation_dims_img)
 
         # calculate the txt bloks
-        txt += apply_mod(self.txt_attn.proj(txt_attn), txt_mod1.gate, None, modulation_dims)
-        txt += apply_mod(self.txt_mlp(apply_mod(self.txt_norm2(txt), (1 + txt_mod2.scale), txt_mod2.shift, modulation_dims)), txt_mod2.gate, None, modulation_dims)
+        txt += apply_mod(self.txt_attn.proj(txt_attn), txt_mod1.gate, None, modulation_dims_txt)
+        txt += apply_mod(self.txt_mlp(apply_mod(self.txt_norm2(txt), (1 + txt_mod2.scale), txt_mod2.shift, modulation_dims_txt)), txt_mod2.gate, None, modulation_dims_txt)
 
         if txt.dtype == torch.float16:
             txt = torch.nan_to_num(txt, nan=0.0, posinf=65504, neginf=-65504)

comfy/ldm/hunyuan_video/model.py

@@ -244,9 +244,11 @@ class HunyuanVideo(nn.Module):
             vec = torch.cat([(vec_ + token_replace_vec).unsqueeze(1), (vec_ + vec).unsqueeze(1)], dim=1)
             frame_tokens = (initial_shape[-1] // self.patch_size[-1]) * (initial_shape[-2] // self.patch_size[-2])
             modulation_dims = [(0, frame_tokens, 0), (frame_tokens, None, 1)]
+            modulation_dims_txt = [(0, None, 1)]
         else:
             vec = vec + self.vector_in(y[:, :self.params.vec_in_dim])
             modulation_dims = None
+            modulation_dims_txt = None
 
         if self.params.guidance_embed:
             if guidance is not None:
@@ -273,14 +275,14 @@ class HunyuanVideo(nn.Module):
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}
-                    out["img"], out["txt"] = block(img=args["img"], txt=args["txt"], vec=args["vec"], pe=args["pe"], attn_mask=args["attention_mask"])
+                    out["img"], out["txt"] = block(img=args["img"], txt=args["txt"], vec=args["vec"], pe=args["pe"], attn_mask=args["attention_mask"], modulation_dims_img=args["modulation_dims_img"], modulation_dims_txt=args["modulation_dims_txt"])
                     return out
 
-                out = blocks_replace[("double_block", i)]({"img": img, "txt": txt, "vec": vec, "pe": pe, "attention_mask": attn_mask}, {"original_block": block_wrap})
+                out = blocks_replace[("double_block", i)]({"img": img, "txt": txt, "vec": vec, "pe": pe, "attention_mask": attn_mask, 'modulation_dims_img': modulation_dims, 'modulation_dims_txt': modulation_dims_txt}, {"original_block": block_wrap})
                 txt = out["txt"]
                 img = out["img"]
             else:
-                img, txt = block(img=img, txt=txt, vec=vec, pe=pe, attn_mask=attn_mask, modulation_dims=modulation_dims)
+                img, txt = block(img=img, txt=txt, vec=vec, pe=pe, attn_mask=attn_mask, modulation_dims_img=modulation_dims, modulation_dims_txt=modulation_dims_txt)
 
             if control is not None: # Controlnet
                 control_i = control.get("input")
@@ -295,10 +297,10 @@ class HunyuanVideo(nn.Module):
             if ("single_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}
-                    out["img"] = block(args["img"], vec=args["vec"], pe=args["pe"], attn_mask=args["attention_mask"])
+                    out["img"] = block(args["img"], vec=args["vec"], pe=args["pe"], attn_mask=args["attention_mask"], modulation_dims=args["modulation_dims"])
                     return out
 
-                out = blocks_replace[("single_block", i)]({"img": img, "vec": vec, "pe": pe, "attention_mask": attn_mask}, {"original_block": block_wrap})
+                out = blocks_replace[("single_block", i)]({"img": img, "vec": vec, "pe": pe, "attention_mask": attn_mask, 'modulation_dims': modulation_dims}, {"original_block": block_wrap})
                 img = out["img"]
             else:
                 img = block(img, vec=vec, pe=pe, attn_mask=attn_mask, modulation_dims=modulation_dims)

comfyui_version.py

 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.3.25"
+__version__ = "0.3.26"

pyproject.toml

 [project]
 name = "ComfyUI"
-version = "0.3.25"
+version = "0.3.26"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.9"