anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Diffusion] Add Boogu Edit-Turbo support docs and tests (#6701)

Browse Source 
Signed-off-by: xRay2016 <1150722393@qq.com>
This commit is contained in:
XRay2016 authored and GitHub committed 2026-09-01 08:41:23 +08:00
1 parent eb11446b7f
commit 8e26dce1f4
8 files changed
+291 -59
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/e2e/online_serving/test_boogu_image_edit.py
+71 -27
View File
@@ -1,15 +1,15 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""
Online serving tests for Boogu-Image-0.1-Edit (image-to-image via chat completions).
Online serving tests for Boogu-Image-0.1-Edit and Edit-Turbo.
The Edit checkpoint shares the ``BooguImagePipeline`` class with the Base
Both Edit checkpoints share the ``BooguImagePipeline`` class with the Base
text-to-image checkpoint; the editing (TI2I) path activates when the request
carries a reference image. Text guidance rides on ``guidance_scale`` (upstream
default 4.0), and image guidance rides on ``guidance_scale_2`` (upstream default
1.0 = off; a value > 1 enables the double-guidance path). Only a single
reference image is supported.
carries a reference image. The regular Edit checkpoint uses text guidance via
``guidance_scale`` and optional image guidance via ``guidance_scale_2``.
Edit-Turbo is guidance-distilled and uses four steps with guidance scale 1.0.
Only a single reference image is supported.
- ``test_single_image_to_image_001``: one reference image, text guidance only.
- ``test_double_guidance_001``: one reference image, text + image guidance.
@@ -40,6 +40,10 @@ pytestmark = [pytest.mark.diffusion, pytest.mark.slow]
EDIT_PROMPT = "Change the style to a colored pencil drawing."
SINGLE_CARD_FEATURE_MARKS = hardware_marks(res={"cuda": "H100"})
EDIT_MODEL = "Boogu/Boogu-Image-0.1-Edit"
EDIT_TURBO_MODEL = "Boogu/Boogu-Image-0.1-Edit-Turbo"
EDIT_TURBO_REVISION = "hotfix-1k-20260708"
def _get_diffusion_feature_cases(model: str):
"""Return one ``default`` ``OmniServerParams`` row for ``model`` (no extra ``server_args``)."""
@@ -54,13 +58,44 @@ def _get_diffusion_feature_cases(model: str):
]
def _get_single_edit_cases():
"""Return the regular and distilled Edit server/request configurations."""
return [
pytest.param(
OmniServerParams(model=EDIT_MODEL),
{
"num_inference_steps": 2,
"guidance_scale": 5.0,
},
id="edit",
marks=SINGLE_CARD_FEATURE_MARKS,
),
pytest.param(
OmniServerParams(
model=EDIT_TURBO_MODEL,
server_args=["--revision", EDIT_TURBO_REVISION],
),
{
"num_inference_steps": 4,
"guidance_scale": 1.0,
},
id="edit-turbo-hotfix-1k",
marks=SINGLE_CARD_FEATURE_MARKS,
),
]
@pytest.mark.parametrize(
"omni_server",
_get_diffusion_feature_cases("Boogu/Boogu-Image-0.1-Edit"),
indirect=True,
("omni_server", "sampling_params"),
_get_single_edit_cases(),
indirect=["omni_server"],
)
def test_single_image_to_image_001(omni_server: OmniServer, openai_client: OpenAIClientHandler):
"""Single-reference text-guided edit smoke for ``Boogu/Boogu-Image-0.1-Edit``."""
def test_single_image_to_image_001(
omni_server: OmniServer,
sampling_params: dict,
openai_client: OpenAIClientHandler,
):
"""Single-reference text-guided edit smoke for regular and Turbo Edit."""
image_data_url = f"data:image/jpeg;base64,{generate_synthetic_image(512, 512)['base64']}"
messages = dummy_messages_from_mix_data(image_data_url=image_data_url, content_text=EDIT_PROMPT)
@@ -69,9 +104,7 @@ def test_single_image_to_image_001(omni_server: OmniServer, openai_client: OpenA
"model": omni_server.model,
"messages": messages,
"extra_body": {
"num_inference_steps": 2,
# Boogu text guidance (upstream default 4.0); > 1 enables CFG.
"guidance_scale": 5.0,
**sampling_params,
"seed": 42,
},
}
@@ -81,7 +114,7 @@ def test_single_image_to_image_001(omni_server: OmniServer, openai_client: OpenA
@pytest.mark.parametrize(
"omni_server",
_get_diffusion_feature_cases("Boogu/Boogu-Image-0.1-Edit"),
_get_diffusion_feature_cases(EDIT_MODEL),
indirect=True,
)
def test_double_guidance_001(omni_server: OmniServer, openai_client: OpenAIClientHandler):
@@ -105,15 +138,20 @@ def test_double_guidance_001(omni_server: OmniServer, openai_client: OpenAIClien
openai_client.send_diffusion_request(request_config)
def _edits_request_config(model: str, *, guidance_scale_2: float | None = None) -> dict:
def _edits_request_config(
model: str,
*,
num_inference_steps: int = 2,
guidance_scale: float = 5.0,
guidance_scale_2: float | None = None,
) -> dict:
"""Multipart ``/v1/images/edits`` config: one synthetic reference + smoke-depth params."""
image_bytes = base64.b64decode(generate_synthetic_image(512, 512)["base64"])
data = {
"model": model,
"prompt": EDIT_PROMPT,
"num_inference_steps": 2,
# Boogu text guidance (upstream default 4.0); > 1 enables CFG.
"guidance_scale": 5.0,
"num_inference_steps": num_inference_steps,
"guidance_scale": guidance_scale,
"seed": 42,
}
if guidance_scale_2 is not None:
@@ -133,19 +171,25 @@ def _assert_edits_response_has_image(responses) -> None:
@pytest.mark.parametrize(
"omni_server",
_get_diffusion_feature_cases("Boogu/Boogu-Image-0.1-Edit"),
indirect=True,
("omni_server", "sampling_params"),
_get_single_edit_cases(),
indirect=["omni_server"],
)
def test_images_edits_endpoint_001(omni_server: OmniServer, openai_client: OpenAIClientHandler):
"""Single-reference text-guided edit via the OpenAI-compatible ``/v1/images/edits`` endpoint."""
responses = openai_client.send_images_edits_http_request(_edits_request_config(omni_server.model))
def test_images_edits_endpoint_001(
omni_server: OmniServer,
sampling_params: dict,
openai_client: OpenAIClientHandler,
):
"""Single-reference regular and Turbo Edit via ``/v1/images/edits``."""
responses = openai_client.send_images_edits_http_request(
_edits_request_config(omni_server.model, **sampling_params)
)
_assert_edits_response_has_image(responses)
@pytest.mark.parametrize(
"omni_server",
_get_diffusion_feature_cases("Boogu/Boogu-Image-0.1-Edit"),
_get_diffusion_feature_cases(EDIT_MODEL),
indirect=True,
)
def test_images_edits_endpoint_double_guidance_001(omni_server: OmniServer, openai_client: OpenAIClientHandler):
tests/e2e/online_serving/test_boogu_image_edit_expansion.py
+48 -11
View File
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""
L4 expansion coverage for ``Boogu/Boogu-Image-0.1-Edit`` (image editing / TI2I).
L4 expansion coverage for Boogu-Image Edit and Edit-Turbo (image editing / TI2I).
The nightly smoke module (``test_boogu_image_edit.py``) already covers single-image
text-guided editing and the text+image double-guidance path. This expansion
@@ -16,11 +16,12 @@ module adds the two edit paths smoke does not exercise:
``height`` / ``width``: asserts the output resolution follows the reference
(upstream ``align_res``, on by default for a single reference).
The Edit checkpoint shares ``BooguImagePipeline`` with the Base checkpoint; the
TI2I path activates when the request carries a reference image. Only a single
reference image is supported. Cases stay smoke-depth (``num_inference_steps=2``).
CPU offload, Cache-DiT, and multi-GPU parallelism are not yet supported for this
model and are intentionally omitted.
Both Edit checkpoints share ``BooguImagePipeline`` with the Base checkpoint;
the TI2I path activates when the request carries a reference image. Only a
single reference image is supported. The regular Edit cases stay smoke-depth
(``num_inference_steps=2``), while Edit-Turbo uses its tuned four-step
configuration. CPU offload, Cache-DiT, and multi-GPU parallelism are not yet
supported for these models and are intentionally omitted.
From ``tests/``::
@@ -41,6 +42,8 @@ os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
pytestmark = [pytest.mark.diffusion, pytest.mark.slow]
MODEL = "Boogu/Boogu-Image-0.1-Edit"
EDIT_TURBO_MODEL = "Boogu/Boogu-Image-0.1-Edit-Turbo"
EDIT_TURBO_REVISION = "hotfix-1k-20260708"
EDIT_PROMPT = "Change the style to a colored pencil drawing."
SINGLE_CARD_FEATURE_MARKS = hardware_marks(res={"cuda": "H100"})
@@ -57,6 +60,33 @@ def _get_diffusion_feature_cases(model: str):
]
def _get_align_res_cases():
"""Return regular and Turbo Edit configurations for align-res coverage."""
return [
pytest.param(
OmniServerParams(model=MODEL),
{
"num_inference_steps": 2,
"guidance_scale": 5.0,
},
id="edit",
marks=SINGLE_CARD_FEATURE_MARKS,
),
pytest.param(
OmniServerParams(
model=EDIT_TURBO_MODEL,
server_args=["--revision", EDIT_TURBO_REVISION],
),
{
"num_inference_steps": 4,
"guidance_scale": 1.0,
},
id="edit-turbo-hotfix-1k",
marks=SINGLE_CARD_FEATURE_MARKS,
),
]
@pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True)
def test_image_only_guidance(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
"""Image-only guidance: text CFG off (1.0), image CFG on (2.0) -> image-only CFG branch."""
@@ -76,8 +106,16 @@ def test_image_only_guidance(omni_server: OmniServer, openai_client: OpenAIClien
openai_client.send_diffusion_request(request_config)
@pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True)
def test_align_res_output_size(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
@pytest.mark.parametrize(
("omni_server", "sampling_params"),
_get_align_res_cases(),
indirect=["omni_server"],
)
def test_align_res_output_size(
omni_server: OmniServer,
sampling_params: dict,
openai_client: OpenAIClientHandler,
) -> None:
"""Output resolution follows the reference image (upstream ``align_res``).
No ``height`` / ``width`` is requested. The reference is 512x384 — both
@@ -92,8 +130,7 @@ def test_align_res_output_size(omni_server: OmniServer, openai_client: OpenAICli
"model": omni_server.model,
"messages": messages,
"extra_body": {
"num_inference_steps": 2,
"guidance_scale": 5.0,
**sampling_params,
"seed": 42,
},
}