2022-06-15 14:21:19 -07:00
[pytest]
2024-02-22 14:55:40 -08:00
addopts = -m "not sequential and not nightly and not inference and not seq_inference and not inference_ops and not inference_v2 and not inference_v2_ops and not stable_diffusion and not evaluation"
2022-06-15 14:21:19 -07:00
markers =
sequential:Tests that need to be run sequentially
inference:Inference model tests
2022-12-13 09:17:00 -08:00
inference_ops:Individual inference operator tests
2024-02-22 14:55:40 -08:00
inference_v2:Inference tests for the v2 stack
inference_v2_ops:Op tests for the v2 stack
2022-09-09 13:31:53 -07:00
seq_inference:Inference model tests to run sequentially
2022-06-15 14:21:19 -07:00
nightly:Tests that should be run nightly
2023-06-28 12:33:55 -07:00
world_size:Change world size of individual tests in a class
Add stable diffusion unit test (#2496)
Add a unit test for Stable Diffusion without using stable-diffusion
model that needs HF token.
Midjourney model does not need the HF token and has the same structure.
We verified this by printing both models. The following is the
structure:
``` StableDiffusionPipeline {
"_class_name": "StableDiffusionPipeline",
"_diffusers_version": "0.7.2",
"feature_extractor": [
"transformers",
"CLIPFeatureExtractor"
],
"safety_checker": [
"stable_diffusion",
"StableDiffusionSafetyChecker"
],
"scheduler": [
"diffusers",
"PNDMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}
```
@cmikeh2
---------
Co-authored-by: Olatunji Ruwase <olruwase@microsoft.com>
Co-authored-by: Logan Adams <114770087+loadams@users.noreply.github.com>
Co-authored-by: Logan Adams <loadams@microsoft.com>
Co-authored-by: Lev Kurilenko <lekurile@microsoft.com>
Co-authored-by: Lev Kurilenko <113481193+lekurile@users.noreply.github.com>
2023-11-13 14:47:09 -08:00
stable_diffusion:Tests that run Stable Diffusion
2024-02-22 14:55:40 -08:00
evaluation:Tests that evaluate model correctness
