[Bugfix] Support both list and generator mode & fix unnecessary error log (#599)

Signed-off-by: Gaohan123 <hgaoaf@connect.ust.hk>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Gao HanandHongsheng Liu authored and GitHub committed 2026-01-05 09:17:06 +08:00
1 parent cb7361f021
commit 6b18d31aaa
22 files changed
+134 -151

No files matched your search

@@ -322,81 +322,76 @@ def main():
print(f" Parallel configuration: ulysses_degree={args.ulysses_degree}, ring_degree={args.ring_degree}")
print(f"{'=' * 60}\n")
try:
generation_start = time.perf_counter()
# Generate edited image
generate_kwargs = {
"prompt": args.prompt,
"pil_image": input_image,
"negative_prompt": args.negative_prompt,
"generator": generator,
"true_cfg_scale": args.cfg_scale,
"guidance_scale": args.guidance_scale,
"num_inference_steps": args.num_inference_steps,
"num_outputs_per_prompt": args.num_outputs_per_prompt,
"layers": args.layers,
"resolution": args.resolution,
}
generation_start = time.perf_counter()
# Generate edited image
generate_kwargs = {
"prompt": args.prompt,
"pil_image": input_image,
"negative_prompt": args.negative_prompt,
"generator": generator,
"true_cfg_scale": args.cfg_scale,
"guidance_scale": args.guidance_scale,
"num_inference_steps": args.num_inference_steps,
"num_outputs_per_prompt": args.num_outputs_per_prompt,
"layers": args.layers,
"resolution": args.resolution,
}
outputs = omni.generate(**generate_kwargs)
generation_end = time.perf_counter()
generation_time = generation_end - generation_start
outputs = omni.generate(**generate_kwargs)
generation_end = time.perf_counter()
generation_time = generation_end - generation_start
# Print profiling results
print(f"Total generation time: {generation_time:.4f} seconds ({generation_time * 1000:.2f} ms)")
# Print profiling results
print(f"Total generation time: {generation_time:.4f} seconds ({generation_time * 1000:.2f} ms)")
# omni.generate() returns Generator[OmniRequestOutput, None, None], convert to list
outputs = list(outputs)
if not outputs:
raise ValueError("No output generated from omni.generate()")
logger.info("Outputs: %s", outputs)
if not outputs:
raise ValueError("No output generated from omni.generate()")
logger.info("Outputs: %s", outputs)
# Extract images from OmniRequestOutput
# omni.generate() returns Generator[OmniRequestOutput, None, None], extract images from request_output[0].images
first_output = outputs[0]
if not hasattr(first_output, "request_output") or not first_output.request_output:
raise ValueError("No request_output found in OmniRequestOutput")
# Extract images from OmniRequestOutput
# omni.generate() returns list[OmniRequestOutput], extract images from request_output[0].images
first_output = outputs[0]
if not hasattr(first_output, "request_output") or not first_output.request_output:
raise ValueError("No request_output found in OmniRequestOutput")
req_out = first_output.request_output[0]
if not isinstance(req_out, OmniRequestOutput) or not hasattr(req_out, "images"):
raise ValueError("Invalid request_output structure or missing 'images' key")
req_out = first_output.request_output[0]
if not isinstance(req_out, OmniRequestOutput) or not hasattr(req_out, "images"):
raise ValueError("Invalid request_output structure or missing 'images' key")
images = req_out.images
if not images:
raise ValueError("No images found in request_output")
images = req_out.images
if not images:
raise ValueError("No images found in request_output")
# Save output image(s)
output_path = Path(args.output)
output_path.parent.mkdir(parents=True, exist_ok=True)
suffix = output_path.suffix or ".png"
stem = output_path.stem or "output_image_edit"
# Save output image(s)
output_path = Path(args.output)
output_path.parent.mkdir(parents=True, exist_ok=True)
suffix = output_path.suffix or ".png"
stem = output_path.stem or "output_image_edit"
# Handle layered output (each image may be a list of layers)
if args.num_outputs_per_prompt <= 1:
img = images[0]
# Handle layered output (each image may be a list of layers)
if args.num_outputs_per_prompt <= 1:
img = images[0]
# Check if this is a layered output (list of images)
if isinstance(img, list):
for sub_idx, sub_img in enumerate(img):
save_path = output_path.parent / f"{stem}_{sub_idx}{suffix}"
sub_img.save(save_path)
print(f"Saved edited image to {os.path.abspath(save_path)}")
else:
img.save(output_path)
print(f"Saved edited image to {os.path.abspath(output_path)}")
else:
for idx, img in enumerate(images):
# Check if this is a layered output (list of images)
if isinstance(img, list):
for sub_idx, sub_img in enumerate(img):
save_path = output_path.parent / f"{stem}_{sub_idx}{suffix}"
save_path = output_path.parent / f"{stem}_{idx}_{sub_idx}{suffix}"
sub_img.save(save_path)
print(f"Saved edited image to {os.path.abspath(save_path)}")
else:
img.save(output_path)
print(f"Saved edited image to {os.path.abspath(output_path)}")
else:
for idx, img in enumerate(images):
# Check if this is a layered output (list of images)
if isinstance(img, list):
for sub_idx, sub_img in enumerate(img):
save_path = output_path.parent / f"{stem}_{idx}_{sub_idx}{suffix}"
sub_img.save(save_path)
print(f"Saved edited image to {os.path.abspath(save_path)}")
else:
save_path = output_path.parent / f"{stem}_{idx}{suffix}"
img.save(save_path)
print(f"Saved edited image to {os.path.abspath(save_path)}")
finally:
omni.close()
save_path = output_path.parent / f"{stem}_{idx}{suffix}"
img.save(save_path)
print(f"Saved edited image to {os.path.abspath(save_path)}")
if __name__ == "__main__":
@@ -118,7 +118,6 @@ def main():
)
# Extract video frames from OmniRequestOutput
frames = list(frames)
if isinstance(frames, list) and len(frames) > 0:
first_item = frames[0]
@@ -151,31 +150,6 @@ def main():
except ImportError:
raise ImportError("diffusers is required for export_to_video.")
# Extract video frames from OmniRequestOutput
if isinstance(frames, list) and len(frames) > 0:
first_item = frames[0]
# Check if it's an OmniRequestOutput
if hasattr(first_item, "final_output_type"):
if first_item.final_output_type != "image":
raise ValueError(
f"Unexpected output type '{first_item.final_output_type}', expected 'image' for video generation."
)
# Pipeline mode: extract from nested request_output
if hasattr(first_item, "is_pipeline_output") and first_item.is_pipeline_output:
if isinstance(first_item.request_output, list) and len(first_item.request_output) > 0:
inner_output = first_item.request_output[0]
if isinstance(inner_output, dict) and "images" in inner_output:
frames = inner_output["images"][0] if inner_output["images"] else None
if frames is None:
raise ValueError("No video frames found in output.")
# Diffusion mode: use direct images field
elif hasattr(first_item, "images") and first_item.images:
frames = first_item.images
else:
raise ValueError("No video frames found in OmniRequestOutput.")
# frames may be np.ndarray (preferred) or torch.Tensor
# export_to_video expects a list of frames with values in [0, 1]
if isinstance(frames, torch.Tensor):
@@ -10,7 +10,7 @@ Get into the example folder
```bash
cd examples/offline_inference/qwen2_5_omni
```
Then run the command below.
Then run the command below. Note: for processing large volume data, it uses py_generator mode, which will return a python generator from Omni class.
```bash
bash run_multiple_prompts.sh
```
@@ -376,7 +376,7 @@ def main(args):
for i, prompt in enumerate(prompts):
prompt["modalities"] = output_modalities
omni_generator = omni_llm.generate(prompts, sampling_params_list)
omni_generator = omni_llm.generate(prompts, sampling_params_list, py_generator=args.py_generator)
# Determine output directory: prefer --output-dir; fallback to --output-wav
output_dir = args.output_dir if getattr(args, "output_dir", None) else args.output_wav
@@ -514,6 +514,12 @@ def parse_args():
default=None,
help="Modalities to use for the prompts.",
)
parser.add_argument(
"--py-generator",
action="store_true",
default=False,
help="Use py_generator mode. The returned type of Omni.generate() is a Python Generator object.",
)
return parser.parse_args()
@@ -1,3 +1,4 @@
python end2end.py --output-wav output_audio \
--query-type text \
--txt-prompts ../qwen3_omni/text_prompts_10.txt
--txt-prompts ../qwen3_omni/text_prompts_10.txt \
--py-generator
@@ -10,7 +10,7 @@ Get into the example folder
```bash
cd examples/offline_inference/qwen3_omni
```
Then run the command below.
Then run the command below. Note: for processing large volume data, it uses py_generator mode, which will return a python generator from Omni class.
```bash
bash run_multiple_prompts.sh
```
@@ -319,7 +319,7 @@ def main(args):
for i, prompt in enumerate(prompts):
prompt["modalities"] = output_modalities
omni_generator = omni_llm.generate(prompts, sampling_params_list)
omni_generator = omni_llm.generate(prompts, sampling_params_list, py_generator=args.py_generator)
# Determine output directory: prefer --output-dir; fallback to --output-wav
output_dir = args.output_dir if getattr(args, "output_dir", None) else args.output_wav
os.makedirs(output_dir, exist_ok=True)
@@ -470,6 +470,12 @@ def parse_args():
default=None,
help="Output modalities to use for the prompts.",
)
parser.add_argument(
"--py-generator",
action="store_true",
default=False,
help="Use py_generator mode. The returned type of Omni.generate() is a Python Generator object.",
)
return parser.parse_args()
@@ -1,3 +1,4 @@
python end2end.py --output-wav output_audio \
--query-type text \
--txt-prompts text_prompts_10.txt
--txt-prompts text_prompts_10.txt \
--py-generator
@@ -16,7 +16,7 @@ if __name__ == "__main__":
omni = Omni(model="Qwen/Qwen-Image")
prompt = "a cup of coffee on the table"
outputs = omni.generate(prompt)
images = list(outputs)[0].request_output[0].images
images = outputs[0].request_output[0].images
images[0].save("coffee.png")
```
@@ -162,9 +162,8 @@ def main():
print(f"Total generation time: {generation_time:.4f} seconds ({generation_time * 1000:.2f} ms)")
# Extract images from OmniRequestOutput
# omni.generate() returns Generator[OmniRequestOutput, None, None], convert to list
outputs = list(outputs)
if not outputs:
# omni.generate() returns list[OmniRequestOutput], extract images from the first output
if not outputs or len(outputs) == 0:
raise ValueError("No output generated from omni.generate()")
logger.info(f"Outputs: {outputs}")
@@ -54,7 +54,6 @@ def main():
flow_shift=args.flow_shift,
)
# omni.generate() returns Generator[OmniRequestOutput, None, None]
frames = omni.generate(
args.prompt,
negative_prompt=args.negative_prompt,
@@ -68,7 +67,6 @@ def main():
)
# Extract video frames from OmniRequestOutput
frames = list(frames)
if isinstance(frames, list) and len(frames) > 0:
first_item = frames[0]
@@ -100,31 +98,6 @@ def main():
except ImportError:
raise ImportError("diffusers is required for export_to_video.")
# Extract video frames from OmniRequestOutput
if isinstance(frames, list) and len(frames) > 0:
first_item = frames[0]
# Check if it's an OmniRequestOutput
if hasattr(first_item, "final_output_type"):
if first_item.final_output_type != "image":
raise ValueError(
f"Unexpected output type '{first_item.final_output_type}', expected 'image' for video generation."
)
# Pipeline mode: extract from nested request_output
if hasattr(first_item, "is_pipeline_output") and first_item.is_pipeline_output:
if isinstance(first_item.request_output, list) and len(first_item.request_output) > 0:
inner_output = first_item.request_output[0]
if isinstance(inner_output, dict) and "images" in inner_output:
frames = inner_output["images"][0] if inner_output["images"] else None
if frames is None:
raise ValueError("No video frames found in output.")
# Diffusion mode: use direct images field
elif hasattr(first_item, "images") and first_item.images:
frames = first_item.images
else:
raise ValueError("No video frames found in OmniRequestOutput.")
# frames may be np.ndarray (preferred) or torch.Tensor
# export_to_video expects a list of frames with values in [0, 1]
if isinstance(frames, torch.Tensor):