tests: add test for probing diffusers model variant type

tests/test_model_probe.py

@@ -4,7 +4,7 @@ import pytest
 from torch import tensor
 
 from invokeai.backend.model_manager import BaseModelType, ModelRepoVariant
-from invokeai.backend.model_manager.config import InvalidModelConfigException
+from invokeai.backend.model_manager.config import InvalidModelConfigException, MainDiffusersConfig, ModelVariantType
 from invokeai.backend.model_manager.probe import (
     CkptType,
     ModelProbe,
@@ -78,3 +78,11 @@ def test_probe_handles_state_dict_with_integer_keys():
     }
     with pytest.raises(InvalidModelConfigException):
         ModelProbe.get_model_type_from_checkpoint(Path("embedding.pt"), state_dict_with_integer_keys)
+
+
+def test_probe_sd1_diffusers_inpainting(datadir: Path):
+    config = ModelProbe.probe(datadir / "sd-1/main/dreamshaper-8-inpainting")
+    assert isinstance(config, MainDiffusersConfig)
+    assert config.base is BaseModelType.StableDiffusion1
+    assert config.variant is ModelVariantType.Inpaint
+    assert config.repo_variant is ModelRepoVariant.FP16

tests/test_model_probe/sd-1/main/dreamshaper-8-inpainting/README

@@ -0,0 +1 @@
+This folder contains config files copied from [Lykon/dreamshaper-8-inpainting](https://huggingface.co/Lykon/dreamshaper-8-inpainting).

tests/test_model_probe/sd-1/main/dreamshaper-8-inpainting/model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionInpaintPipeline",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "lykon-models/dreamshaper-8-inpainting",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DEISMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

tests/test_model_probe/sd-1/main/dreamshaper-8-inpainting/scheduler/scheduler_config.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "DEISMultistepScheduler",
+  "_diffusers_version": "0.21.0.dev0",
+  "algorithm_type": "deis",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "logrho",
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

tests/test_model_probe/sd-1/main/dreamshaper-8-inpainting/unet/config.json

@@ -0,0 +1,66 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--lykon-models--dreamshaper-8-inpainting/snapshots/15dcb9dec91a39ee498e3917c9ef6174b103862d/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 9,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": false
+}