Skip to content

[Bugfix] Fix image edit RoPE crash when explicit height/width are provided #1265

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
hsliuustc0106 merged 4 commits into from
Feb 10, 2026
+14 −11
Merged

[Bugfix] Fix image edit RoPE crash when explicit height/width are provided #1265

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3757b3f
initial commit
lishunyang12 Feb 7, 2026
dae10db
fix: solve large file passing in issue
lishunyang12 Feb 7, 2026
f3d5e5f
fix precommit
lishunyang12 Feb 7, 2026
322ba1d
Merge branch 'main' into online
hsliuustc0106 Feb 10, 2026
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: 4 additions & 0 deletions examples/online_serving/image_to_image/openai_chat_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,10 @@ def edit_image(

# Build extra_body with generation parameters
extra_body = {}
if height is not None:
extra_body["height"] = height
if width is not None:
extra_body["width"] = width
Comment on lines +79 to +82
Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot Feb 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Allow omitting explicit height/width in chat client

After this change, edit_image forwards height/width whenever they are non-None, but main() still sets both CLI args to default 1024, so running the documented command without --height/--width now always sends square dimensions and disables the server’s auto aspect-ratio sizing path for non-square inputs. This is a behavior regression introduced by wiring these fields; if the intent is “optional explicit dims,” the parser defaults need to be None (or equivalent flag-presence detection) so omitted flags stay omitted in extra_body.

Useful? React with 👍 / 👎.

if steps is not None:
extra_body["num_inference_steps"] = steps
if guidance_scale is not None:
Expand Down
2 changes: 0 additions & 2 deletions examples/online_serving/image_to_image/run_curl_image_edit.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,8 +31,6 @@ REQUEST_JSON=$(
]
}],
extra_body: {
height: 1024,
width: 1024,
num_inference_steps: 50,
guidance_scale: 1,
seed: 42
Expand Down
4 changes: 2 additions & 2 deletions vllm_omni/diffusion/models/qwen_image/pipeline_qwen_image_edit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,9 +110,9 @@ def pre_process_func(
if image is not None and not (
isinstance(image, torch.Tensor) and len(image.shape) > 1 and image.shape[1] == latent_channels
):
image = image_processor.resize(image, height, width)
image = image_processor.resize(image, calculated_height, calculated_width)
prompt_image = image
image = image_processor.preprocess(image, height, width)
image = image_processor.preprocess(image, calculated_height, calculated_width)
image = image.unsqueeze(2)

# Store preprocessed image and prompt image in request
Expand Down