Yao Matrix c51b6bd837 introduce compute arch specific expectations and fix test_sd3_img2img_inference failure (#11227) ...

* add arch specfic expectations support, to support different arch's numerical characteristics

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* fix typo

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* Apply suggestions from code review

* Apply style fixes

* Update src/diffusers/utils/testing_utils.py

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

2025-04-08 14:57:49 +01:00

..

allegro

Module Group Offloading (#10503)

2025-02-14 12:59:45 +05:30

amused

Module Group Offloading (#10503)

2025-02-14 12:59:45 +05:30

animatediff

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

audioldm

[FEAT] DDUF format (#10037)

2025-01-14 13:21:42 +05:30

audioldm2

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

aura_flow

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

blipdiffusion

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

cogvideo

[core] FasterCache (#10163)

2025-03-21 09:35:04 +05:30

cogview3

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

cogview4

CogView4 (supports different length c and uc) (#10649)

2025-02-15 21:46:48 +05:30

consisid

Module Group Offloading (#10503)

2025-02-14 12:59:45 +05:30

consistency_models

Memory clean up on all Slow Tests (#7514)

2024-03-29 14:23:28 +05:30

controlnet

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

controlnet_flux

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

controlnet_hunyuandit

[tests] HunyuanDiTControlNetPipeline inference precision issue on XPU (#11197)

2025-04-02 12:45:02 +01:00

controlnet_sd3

[tests] make cuda only tests device-agnostic (#11058)

2025-03-20 10:12:35 +00:00

controlnet_xs

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

dance_diffusion

Memory clean up on all Slow Tests (#7514)

2024-03-29 14:23:28 +05:30

ddim

[tests] make tests device-agnostic (part 3) (#10437)

2025-01-21 12:15:45 +00:00

ddpm

[tests] make tests device-agnostic (part 3) (#10437)

2025-01-21 12:15:45 +00:00

deepfloyd_if

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

dit

[Core] Introduce class variants for Transformer2DModel (#7647)

2024-05-31 13:40:27 +05:30

easyanimate

Add EasyAnimateV5.1 text-to-video, image-to-video, control-to-video generation model (#10626)

2025-03-03 18:37:19 +05:30

flux

[core] FasterCache (#10163)

2025-03-21 09:35:04 +05:30

hunyuan_video

New HunyuanVideo-I2V (#11066)

2025-03-24 21:18:40 +05:30

hunyuandit

[tests] fix tests for save load components (#10977)

2025-03-06 12:30:37 +05:30

i2vgen_xl

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

ip_adapters

[tests] enable bnb tests on xpu (#11001)

2025-03-19 16:33:11 +00:00

kandinsky

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

kandinsky2_2

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

kandinsky3

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

kolors

Don't override torch_dtype and don't use when quantization_config is set (#11039)

2025-03-21 21:58:38 +05:30

latent_consistency_models

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

latent_diffusion

make pipelines tests device-agnostic (part1) (#9399)

2024-11-22 15:32:54 +05:30

latte

[core] FasterCache (#10163)

2025-03-21 09:35:04 +05:30

ledits_pp

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

ltx

LTX 0.9.5 (#10968)

2025-03-17 16:43:36 -10:00

lumina

Rename Lumina(2)Text2ImgPipeline -> Lumina(2)Pipeline (#10827)

2025-03-13 09:24:21 -10:00

lumina2

Rename Lumina(2)Text2ImgPipeline -> Lumina(2)Pipeline (#10827)

2025-03-13 09:24:21 -10:00

marigold

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

mochi

[core] FasterCache (#10163)

2025-03-21 09:35:04 +05:30

musicldm

[FEAT] DDUF format (#10037)

2025-01-14 13:21:42 +05:30

omnigen

Refactor OmniGen (#10771)

2025-02-12 14:06:14 +05:30

pag

Don't override torch_dtype and don't use when quantization_config is set (#11039)

2025-03-21 21:58:38 +05:30

paint_by_example

[FEAT] DDUF format (#10037)

2025-01-14 13:21:42 +05:30

pia

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

pixart_alpha

[tests] fix tests for save load components (#10977)

2025-03-06 12:30:37 +05:30

pixart_sigma

[tests] fix tests for save load components (#10977)

2025-03-06 12:30:37 +05:30

pndm

[Tests] Update a deprecated parameter in test files and fix several typos (#7277)

2024-03-14 12:17:35 -07:00

sana

add sana-sprint (#11074)

2025-03-21 06:21:18 -10:00

semantic_stable_diffusion

make pipelines tests device-agnostic (part1) (#9399)

2024-11-22 15:32:54 +05:30

shap_e

[FEAT] DDUF format (#10037)

2025-01-14 13:21:42 +05:30

stable_audio

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

stable_cascade

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

stable_diffusion

[tests] make cuda only tests device-agnostic (#11058)

2025-03-20 10:12:35 +00:00

stable_diffusion_2

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

stable_diffusion_3

introduce compute arch specific expectations and fix test_sd3_img2img_inference failure (#11227)

2025-04-08 14:57:49 +01:00

stable_diffusion_adapter

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

stable_diffusion_gligen

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

stable_diffusion_gligen_text_image

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

stable_diffusion_image_variation

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

stable_diffusion_k_diffusion

Memory clean up on all Slow Tests (#7514)

2024-03-29 14:23:28 +05:30

stable_diffusion_ldm3d

Memory clean up on all Slow Tests (#7514)

2024-03-29 14:23:28 +05:30

stable_diffusion_panorama

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

stable_diffusion_safe

make pipelines tests device-agnostic (part1) (#9399)

2024-11-22 15:32:54 +05:30

stable_diffusion_sag

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

stable_diffusion_xl

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

stable_unclip

[tests] test encode_prompt() in isolation (#10438)

2025-02-20 13:21:43 +05:30

stable_video_diffusion

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

text_to_video_synthesis

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

unclip

[tests] make cuda only tests device-agnostic (#11058)

2025-03-20 10:12:35 +00:00

unidiffuser

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

wan

[WIP] Add Wan Video2Video (#11053)

2025-04-01 17:22:11 +05:30

wuerstchen

[tests] make tests device-agnostic (part 4) (#10508)

2025-03-04 08:26:06 +00:00

__init__.py

Reorganize pipeline tests (#963)

2022-10-24 16:34:01 +02:00

pipeline_params.py

AnimateDiff Video to Video (#6328)

2024-01-24 18:22:26 +05:30

test_pipeline_utils.py

Fix deterministic issue when getting pipeline dtype and device (#10696)

2025-03-15 07:50:58 +05:30

test_pipelines_auto.py

a few fix for SingleFile tests (#9522)

2024-09-24 13:36:53 -10:00

test_pipelines_combined.py

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00

test_pipelines_common.py

Revert save_model in ModelMixin save_pretrained and use safe_serialization=False in test (#11196)

2025-04-02 12:45:36 +01:00

test_pipelines_flax.py

Discourage using deprecated revision parameter (#8573)

2024-06-24 10:06:49 -07:00

test_pipelines_onnx_common.py

[Tests] parallelize (#3078)

2023-04-13 13:32:57 +01:00

test_pipelines.py

[LoRA] Implement hot-swapping of LoRA (#9453)

2025-04-08 17:05:31 +05:30