Skip to content

Change Framepack transformer layer initialization order #11535

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 9, 2025
Merged

Change Framepack transformer layer initialization order #11535

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions src/diffusers/models/transformers/transformer_hunyuan_video_framepack.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,9 +152,19 @@ def __init__(

# 1. Latent and condition embedders
self.x_embedder = HunyuanVideoPatchEmbed((patch_size_t, patch_size, patch_size), in_channels, inner_dim)

# Framepack history projection embedder
self.clean_x_embedder = None
if has_clean_x_embedder:
self.clean_x_embedder = HunyuanVideoHistoryPatchEmbed(in_channels, inner_dim)

self.context_embedder = HunyuanVideoTokenRefiner(
text_embed_dim, num_attention_heads, attention_head_dim, num_layers=num_refiner_layers
)

# Framepack image-conditioning embedder
self.image_projection = FramepackClipVisionProjection(image_proj_dim, inner_dim) if has_image_proj else None

self.time_text_embed = HunyuanVideoConditionEmbedding(
inner_dim, pooled_projection_dim, guidance_embeds, image_condition_type
)
Expand Down Expand Up @@ -186,13 +196,6 @@ def __init__(
self.norm_out = AdaLayerNormContinuous(inner_dim, inner_dim, elementwise_affine=False, eps=1e-6)
self.proj_out = nn.Linear(inner_dim, patch_size_t * patch_size * patch_size * out_channels)

# Framepack specific modules
self.image_projection = FramepackClipVisionProjection(image_proj_dim, inner_dim) if has_image_proj else None

self.clean_x_embedder = None
if has_clean_x_embedder:
self.clean_x_embedder = HunyuanVideoHistoryPatchEmbed(in_channels, inner_dim)

self.use_gradient_checkpointing = False

def forward(
Expand Down