AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

Change Framepack transformer layer initialization order (#11535)

Browse Source 
update
This commit is contained in:
Aryan
2025-05-09 23:09:50 +05:30
committed by GitHub
parent 0ba1f76d4d
commit 92fe689f06
1 changed files with 10 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
src/diffusers/models/transformers/transformer_hunyuan_video_framepack.py
View File

@@ -152,9 +152,19 @@ class HunyuanVideoFramepackTransformer3DModel(
# 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
)
@@ -186,13 +196,6 @@ class HunyuanVideoFramepackTransformer3DModel(
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(