Skip to content

[Feature] online HunyuanImage-3.0 IT2I (image editing) support #3410

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 1 commit into from
May 8, 2026
+14 −0
Merged

[Feature] online HunyuanImage-3.0 IT2I (image editing) support #3410

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
5 changes: 5 additions & 0 deletions vllm_omni/entrypoints/openai/api_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1696,10 +1696,12 @@ async def edit_images(
# vllm-omni extension for layered models (e.g., Qwen-Image-Layered)
layers: int | None = Form(None),
resolution: int | None = Form(None), # See SUPPORTED_LAYERED_RESOLUTIONS
bot_task: str | None = Form(None),
) -> ImageGenerationResponse:
"""
OpenAI-compatible image edit endpoint.
"""

# 1. get engine and model
engine_client, model_name, stage_configs = _get_engine_and_model(raw_request)
if model is not None and model != model_name:
Expand Down Expand Up @@ -1899,6 +1901,8 @@ async def edit_images(
lora_dict = _get_lora_from_json_str(lora)
_parse_lora_request(lora_dict)
extra_body["lora"] = lora_dict
if bot_task is not None:
extra_body["bot_task"] = bot_task

prompt_text = prompt.get("prompt", "")
generation_result = await chat_handler.generate_diffusion_images(
Expand Down Expand Up @@ -2218,6 +2222,7 @@ async def _load_input_images(
images.append(img)
except Exception as e:
raise ValueError(f"Failed to open uploaded file: {e}")

else:
raise ValueError(f"Unsupported input: {inp}")

Expand Down
9 changes: 9 additions & 0 deletions vllm_omni/entrypoints/openai/serving_chat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2148,6 +2148,7 @@ def _build_multistage_generation_inputs(
lora_body = extra_body.get("lora")
layers = extra_body.get("layers")
resolution = extra_body.get("resolution")
bot_task = extra_body.get("bot_task")

Copy link
Copy Markdown
Collaborator

@hsliuustc0106 hsliuustc0106 May 7, 2026

Choose a reason for hiding this comment

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

Debug print statement should be removed before merge.

Copy link
Copy Markdown
Contributor Author

@skf-1999 skf-1999 May 7, 2026

Choose a reason for hiding this comment

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

Removed.

engine_prompt_data: dict[str, Any] | None = None
modalities = ["image"]
Expand All @@ -2158,6 +2159,14 @@ def _build_multistage_generation_inputs(
else:
engine_prompt_data = {"image": reference_images}

if bot_task:
from vllm_omni.diffusion.models.hunyuan_image3.prompt_utils import build_prompt

prompt = build_prompt(prompt, task=bot_task)
if reference_images and len(reference_images) == 1:
engine_prompt_data = {"image": reference_images[0]}
modalities = ["image"]

engine_prompt: OmniTextPrompt = {"prompt": prompt}
engine_prompt["modalities"] = modalities
if negative_prompt is not None:
Expand Down
Loading