andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
comfyanonymous
2025-03-09 04:59:15 -04:00
parent 528d1b3563
commit 9aac21f894
4 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
comfy/ldm/hunyuan_video/model.py
View File

@@ -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)