Skip to content

Fix: ensure RGBA images are converted to RGB before resizing #2

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
hahminlew wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix: ensure RGBA images are converted to RGB before resizing #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0cd5989
fix bug in import attention_processor
hahminlew Sep 23, 2025
924e128
fix: convert RGBA to RGB before resize to prevent channel mismatch
hahminlew Sep 23, 2025
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
4 changes: 2 additions & 2 deletions infer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ def edit_image(
final_timestep = torch.ones((1,), dtype=torch.int64, device="cuda") * 999

# Input Image
pil_img_cond = Image.open(img_path).resize((512, 512))
pil_img_cond = Image.open(img_path).convert("RGB").resize((512, 512))

processed_image = to_tensor(pil_img_cond).unsqueeze(0).to("cuda") * 2 - 1

Expand Down Expand Up @@ -110,4 +110,4 @@ def edit_image(
start_time = time.time()
result = edit_image(img_path, src_p, edit_p, inverse_model, aux_model, ip_sb_model)
print(f"Edit {src_p}->{edit_p} in {time.time()-start_time}")
save_image(result, f"result_{src_p}->{edit_p}.png")
save_image(result, f"result_{src_p}->{edit_p}.png")
6 changes: 3 additions & 3 deletions models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,9 @@
)

from src.mask_ip_controller import *
from src.ip_adapter.attention_processor import AttnProcessor2_0 as AttnProcessor
from src.ip_adapter.attention_processor import IPAttnProcessor2_0 as IPAttnProcessor
from src.ip_adapter.mask_attention_processor import IPAttnProcessor2_0WithIPMaskController
from src.attention_processor import AttnProcessor2_0 as AttnProcessor
from src.attention_processor import IPAttnProcessor2_0 as IPAttnProcessor
from src.mask_attention_processor import IPAttnProcessor2_0WithIPMaskController

def tokenize_captions(tokenizer, captions):
inputs = tokenizer(
Expand Down