From 340cba7b04237e5374f4e3642483117f4bfc42b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B1=AA=E5=BF=97=E9=B9=8F?= Date: Tue, 7 Apr 2026 17:16:12 +0800 Subject: [PATCH] [daVinci-MagiHuman][Doc][BugFix] Update model support for daVici-MagiHuman and fix media utils bug (#2542) Signed-off-by: princepride --- docs/models/supported_models.md | 2 +- docs/user_guide/diffusion_features.md | 2 +- tests/e2e/offline_inference/test_magi_human.py | 2 +- vllm_omni/diffusion/utils/media_utils.py | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md index f3d22aa76..8eab20edc 100644 --- a/docs/models/supported_models.md +++ b/docs/models/supported_models.md @@ -37,7 +37,7 @@ th { | `LTX2TwoStagesPipeline` | LTX-2-T2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | | | `LTX2ImageToVideoTwoStagesPipeline` | LTX-2-I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | | | `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | | -| `MagiHumanPipeline` | MagiHuman | `princepride/daVinci-MagiHuman` | ✅︎ | ✅︎ | | | +| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | | | `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ | | `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | | `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | diff --git a/docs/user_guide/diffusion_features.md b/docs/user_guide/diffusion_features.md index c151164ca..d4d9ce6a3 100644 --- a/docs/user_guide/diffusion_features.md +++ b/docs/user_guide/diffusion_features.md @@ -124,7 +124,7 @@ The following tables show which models support each feature: > Notes: > 1. Nextstep_1(T2I) does not support cache acceleration methods such as TeaCache or Cache-DiT. -> 2. `Tongyi-MAI/Z-Image-Turbo` and `princepride/daVinci-MagiHuman` are distilled models with minimal NFEs; CFG-Parallel is not necessary. +> 2. `Tongyi-MAI/Z-Image-Turbo` and `SII-GAIR/daVinci-MagiHuman-Base-1080p` are distilled models with minimal NFEs; CFG-Parallel is not necessary. ### VideoGen diff --git a/tests/e2e/offline_inference/test_magi_human.py b/tests/e2e/offline_inference/test_magi_human.py index 6211fdafc..cb711edb5 100644 --- a/tests/e2e/offline_inference/test_magi_human.py +++ b/tests/e2e/offline_inference/test_magi_human.py @@ -47,7 +47,7 @@ def test_magi_human_e2e(run_level): if run_level != "advanced_model": pytest.skip("MagiHuman e2e test requires advanced_model run level with real weights.") - model_path = "princepride/daVinci-MagiHuman" + model_path = "SII-GAIR/daVinci-MagiHuman-Base-1080p" omni = Omni( model=model_path, diff --git a/vllm_omni/diffusion/utils/media_utils.py b/vllm_omni/diffusion/utils/media_utils.py index ee1f8116f..f96a28fbd 100644 --- a/vllm_omni/diffusion/utils/media_utils.py +++ b/vllm_omni/diffusion/utils/media_utils.py @@ -50,7 +50,7 @@ def mux_video_audio_bytes( if samples.ndim == 1: samples = samples.reshape(1, -1) elif samples.ndim == 2 and samples.shape[0] > samples.shape[1]: - samples = samples.T + samples = np.ascontiguousarray(samples.T) num_channels = samples.shape[0] layout = "stereo" if num_channels >= 2 else "mono" a_stream = container.add_stream(audio_codec, rate=audio_sample_rate)