Skip to content

Cosmos Transfer2.5 Auto-Regressive Inference Pipeline #13114

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

Open
miguelmartin75 wants to merge 1 commit into
base: main
Choose a base branch
from
+412 −226
Open

Cosmos Transfer2.5 Auto-Regressive Inference Pipeline #13114

Show file tree
Hide file tree
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
24 changes: 21 additions & 3 deletions scripts/convert_cosmos_to_diffusers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,9 +94,15 @@
--transformer_type Cosmos-2.5-Transfer-General-2B \
--transformer_ckpt_path $transformer_ckpt_path \
--vae_type wan2.1 \
--output_path converted/transfer/2b/general/depth \
--output_path converted/transfer/2b/general/depth/pipeline \
--save_pipeline

python scripts/convert_cosmos_to_diffusers.py \
--transformer_type Cosmos-2.5-Transfer-General-2B \
--transformer_ckpt_path $transformer_ckpt_path \
--vae_type wan2.1 \
--output_path converted/transfer/2b/general/depth/models

# edge
transformer_ckpt_path=~/.cache/huggingface/hub/models--nvidia--Cosmos-Transfer2.5-2B/snapshots/eb5325b77d358944da58a690157dd2b8071bbf85/general/edge/61f5694b-0ad5-4ecd-8ad7-c8545627d125_ema_bf16.pt

Expand All @@ -120,18 +126,30 @@
--transformer_type Cosmos-2.5-Transfer-General-2B \
--transformer_ckpt_path $transformer_ckpt_path \
--vae_type wan2.1 \
--output_path converted/transfer/2b/general/blur \
--output_path converted/transfer/2b/general/blur/pipeline \
--save_pipeline

python scripts/convert_cosmos_to_diffusers.py \
--transformer_type Cosmos-2.5-Transfer-General-2B \
--transformer_ckpt_path $transformer_ckpt_path \
--vae_type wan2.1 \
--output_path converted/transfer/2b/general/blur/models

# seg
transformer_ckpt_path=~/.cache/huggingface/hub/models--nvidia--Cosmos-Transfer2.5-2B/snapshots/eb5325b77d358944da58a690157dd2b8071bbf85/general/seg/5136ef49-6d8d-42e8-8abf-7dac722a304a_ema_bf16.pt

python scripts/convert_cosmos_to_diffusers.py \
--transformer_type Cosmos-2.5-Transfer-General-2B \
--transformer_ckpt_path $transformer_ckpt_path \
--vae_type wan2.1 \
--output_path converted/transfer/2b/general/seg \
--output_path converted/transfer/2b/general/seg/pipeline \
--save_pipeline

python scripts/convert_cosmos_to_diffusers.py \
--transformer_type Cosmos-2.5-Transfer-General-2B \
--transformer_ckpt_path $transformer_ckpt_path \
--vae_type wan2.1 \
--output_path converted/transfer/2b/general/seg/models
```
"""

Expand Down
7 changes: 6 additions & 1 deletion src/diffusers/models/controlnets/controlnet_cosmos.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,7 +191,12 @@ def forward(
dim=1,
)

control_hidden_states = torch.cat([control_hidden_states, torch.zeros_like(controls_latents[:, :1])], dim=1)
if condition_mask is not None:
control_hidden_states = torch.cat([control_hidden_states, condition_mask], dim=1)
else:
control_hidden_states = torch.cat(
[control_hidden_states, torch.zeros_like(controls_latents[:, :1])], dim=1
)

padding_mask_resized = transforms.functional.resize(
padding_mask, list(control_hidden_states.shape[-2:]), interpolation=transforms.InterpolationMode.NEAREST
Expand Down
Loading