Skip to content

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 for HunyuanVideo1.5 meanflow distil (#11212)

Jukka Seppänene2a800e7ef22
diff --git a/comfy/ldm/hunyuan_video/model.py b/comfy/ldm/hunyuan_video/model.py
index 2749c53f5..55ab550f8 100644
--- a/comfy/ldm/hunyuan_video/model.py
+++ b/comfy/ldm/hunyuan_video/model.py
@@ -43,6 +43,7 @@ class HunyuanVideoParams:
meanflow: bool
use_cond_type_embedding: bool
vision_in_dim: int
+ meanflow_sum: bool
class SelfAttentionRef(nn.Module):
@@ -317,7 +318,7 @@ class HunyuanVideo(nn.Module):
timesteps_r = transformer_options['sample_sigmas'][w[0] + 1]
timesteps_r = timesteps_r.unsqueeze(0).to(device=timesteps.device, dtype=timesteps.dtype)
vec_r = self.time_r_in(timestep_embedding(timesteps_r, 256, time_factor=1000.0).to(img.dtype))
- vec = (vec + vec_r) / 2
+ vec = (vec + vec_r) if self.params.meanflow_sum else (vec + vec_r) / 2
if ref_latent is not None:
ref_latent_ids = self.img_ids(ref_latent)
diff --git a/comfy/model_detection.py b/comfy/model_detection.py
index 19e6aa954..1f5d34bdd 100644
--- a/comfy/model_detection.py
+++ b/comfy/model_detection.py
@@ -180,8 +180,10 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
dit_config["use_cond_type_embedding"] = False
if '{}vision_in.proj.0.weight'.format(key_prefix) in state_dict_keys:
dit_config["vision_in_dim"] = state_dict['{}vision_in.proj.0.weight'.format(key_prefix)].shape[0]
+ dit_config["meanflow_sum"] = True
else:
dit_config["vision_in_dim"] = None
+ dit_config["meanflow_sum"] = False
return dit_config
if '{}double_blocks.0.img_attn.norm.key_norm.scale'.format(key_prefix) in state_dict_keys and ('{}img_in.weight'.format(key_prefix) in state_dict_keys or f"{key_prefix}distilled_guidance_layer.norms.0.scale" in state_dict_keys): #Flux, Chroma or Chroma Radiance (has no img_in.weight)