[Bugfix] Limit Qwen-Image-Edit-2511 input image count (#2840)

Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
WeiQing ChenandGao Han authored and GitHub committed 2026-04-17 20:07:30 +08:00
1 parent b7f239810d
commit f658bcb0bf
7 files changed
+183 -9

No files matched your search

+9 -2
View File
@@ -18,6 +18,7 @@ from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig,
)
from vllm_omni.diffusion.model_metadata import get_diffusion_model_metadata
from vllm_omni.diffusion.utils.network_utils import is_port_available
from vllm_omni.quantization import build_quant_config
@@ -481,8 +482,10 @@ class OmniDiffusionConfig:
# Scheduler flow_shift for Wan2.2 (12.0 for 480p, 5.0 for 720p)
flow_shift: float | None = None
# support multi images input
# Support multi-image inputs and expose any model-specific request limit
# through a generic config field so serving code stays model-agnostic.
supports_multimodal_inputs: bool = False
max_multimodal_image_inputs: int | None = None
log_level: str = "info"
@@ -664,7 +667,11 @@ class OmniDiffusionConfig:
)
def update_multimodal_support(self) -> None:
self.supports_multimodal_inputs = self.model_class_name in {"QwenImageEditPlusPipeline"}
# Resolve serving-visible multimodal behavior from shared metadata
# instead of importing concrete pipeline modules into the config layer.
metadata = get_diffusion_model_metadata(self.model_class_name)
self.supports_multimodal_inputs = metadata.supports_multimodal_inputs
self.max_multimodal_image_inputs = metadata.max_multimodal_image_inputs
def enrich_config(self) -> None:
"""Load model metadata from HuggingFace and populate config fields.
+31
View File
@@ -0,0 +1,31 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from dataclasses import dataclass
@dataclass(frozen=True)
class DiffusionModelMetadata:
# Keep serving-facing capability metadata in a lightweight shared module so
# config/model plumbing can read it without importing concrete pipelines.
supports_multimodal_inputs: bool = False
max_multimodal_image_inputs: int | None = None
QWEN_IMAGE_EDIT_PLUS_MAX_INPUT_IMAGES = 4
_DIFFUSION_MODEL_METADATA: dict[str, DiffusionModelMetadata] = {
"QwenImageEditPlusPipeline": DiffusionModelMetadata(
supports_multimodal_inputs=True,
max_multimodal_image_inputs=QWEN_IMAGE_EDIT_PLUS_MAX_INPUT_IMAGES,
),
}
def get_diffusion_model_metadata(model_class_name: str | None) -> DiffusionModelMetadata:
# Unknown models fall back to "no special multimodal capabilities" so new
# pipelines do not accidentally inherit limits meant for other models.
if model_class_name is None:
return DiffusionModelMetadata()
return _DIFFUSION_MODEL_METADATA.get(model_class_name, DiffusionModelMetadata())
@@ -25,6 +25,7 @@ from vllm.model_executor.models.utils import AutoWeightsLoader
from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
from vllm_omni.diffusion.distributed.utils import get_local_device
from vllm_omni.diffusion.model_loader.diffusers_loader import DiffusersPipelineLoader
from vllm_omni.diffusion.model_metadata import QWEN_IMAGE_EDIT_PLUS_MAX_INPUT_IMAGES
from vllm_omni.diffusion.models.interface import SupportImageInput
from vllm_omni.diffusion.models.qwen_image.cfg_parallel import (
QwenImageCFGParallelMixin,
@@ -56,6 +57,12 @@ logger = logging.getLogger(__name__)
CONDITION_IMAGE_SIZE = 384 * 384
VAE_IMAGE_SIZE = 1024 * 1024
# Keep this in sync with the practical conditioning-token budget for
# Qwen-Image-Edit-2511. Empirically, 4 images stays within the supported range
# while 5 images overflows the prompt/conditioning path and fails downstream.
# Re-export the shared metadata value locally so this pipeline keeps a nearby,
# descriptive constant for validation and tests without becoming the source of truth.
MAX_QWEN_IMAGE_EDIT_PLUS_INPUT_IMAGES = QWEN_IMAGE_EDIT_PLUS_MAX_INPUT_IMAGES
def get_qwen_image_edit_plus_pre_process_func(
@@ -93,6 +100,11 @@ def get_qwen_image_edit_plus_pre_process_func(
if not isinstance(raw_image, list):
raw_image = [raw_image]
if len(raw_image) > MAX_QWEN_IMAGE_EDIT_PLUS_INPUT_IMAGES:
raise ValueError(
f"Received {len(raw_image)} input images. "
f"At most {MAX_QWEN_IMAGE_EDIT_PLUS_INPUT_IMAGES} images are supported by this model."
)
image = [
PIL.Image.open(im) if isinstance(im, str) else cast(PIL.Image.Image | np.ndarray | torch.Tensor, im)
for im in raw_image