[CI] Multiple Slow Test fixes. (#9198)

* update

* update

* update

* update

Author: DN6

tests/lora/test_lora_layers_sd3.py

@@ -32,7 +32,7 @@
 @require_peft_backend
 class SD3LoRATests(unittest.TestCase, PeftLoraLoaderMixinTests):
     pipeline_class = StableDiffusion3Pipeline
-    scheduler_cls = FlowMatchEulerDiscreteScheduler()
+    scheduler_cls = FlowMatchEulerDiscreteScheduler
     scheduler_kwargs = {}
     uses_flow_matching = True
     transformer_kwargs = {
@@ -80,8 +80,7 @@ def test_sd3_lora(self):
         Related PR: https://github.com/huggingface/diffusers/pull/8584
         """
         components = self.get_dummy_components()
-
-        pipe = self.pipeline_class(**components)
+        pipe = self.pipeline_class(**components[0])
         pipe = pipe.to(torch_device)
         pipe.set_progress_bar_config(disable=None)
 

tests/lora/test_lora_layers_sdxl.py

@@ -124,71 +124,6 @@ def tearDown(self):
         gc.collect()
         torch.cuda.empty_cache()
 
-    def test_sdxl_0_9_lora_one(self):
-        generator = torch.Generator().manual_seed(0)
-
-        pipe = StableDiffusionXLPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-0.9")
-        lora_model_id = "hf-internal-testing/sdxl-0.9-daiton-lora"
-        lora_filename = "daiton-xl-lora-test.safetensors"
-        pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
-        pipe.enable_model_cpu_offload()
-
-        images = pipe(
-            "masterpiece, best quality, mountain", output_type="np", generator=generator, num_inference_steps=2
-        ).images
-
-        images = images[0, -3:, -3:, -1].flatten()
-        expected = np.array([0.3838, 0.3482, 0.3588, 0.3162, 0.319, 0.3369, 0.338, 0.3366, 0.3213])
-
-        max_diff = numpy_cosine_similarity_distance(expected, images)
-        assert max_diff < 1e-3
-        pipe.unload_lora_weights()
-        release_memory(pipe)
-
-    def test_sdxl_0_9_lora_two(self):
-        generator = torch.Generator().manual_seed(0)
-
-        pipe = StableDiffusionXLPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-0.9")
-        lora_model_id = "hf-internal-testing/sdxl-0.9-costumes-lora"
-        lora_filename = "saijo.safetensors"
-        pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
-        pipe.enable_model_cpu_offload()
-
-        images = pipe(
-            "masterpiece, best quality, mountain", output_type="np", generator=generator, num_inference_steps=2
-        ).images
-
-        images = images[0, -3:, -3:, -1].flatten()
-        expected = np.array([0.3137, 0.3269, 0.3355, 0.255, 0.2577, 0.2563, 0.2679, 0.2758, 0.2626])
-
-        max_diff = numpy_cosine_similarity_distance(expected, images)
-        assert max_diff < 1e-3
-
-        pipe.unload_lora_weights()
-        release_memory(pipe)
-
-    def test_sdxl_0_9_lora_three(self):
-        generator = torch.Generator().manual_seed(0)
-
-        pipe = StableDiffusionXLPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-0.9")
-        lora_model_id = "hf-internal-testing/sdxl-0.9-kamepan-lora"
-        lora_filename = "kame_sdxl_v2-000020-16rank.safetensors"
-        pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
-        pipe.enable_model_cpu_offload()
-
-        images = pipe(
-            "masterpiece, best quality, mountain", output_type="np", generator=generator, num_inference_steps=2
-        ).images
-
-        images = images[0, -3:, -3:, -1].flatten()
-        expected = np.array([0.4015, 0.3761, 0.3616, 0.3745, 0.3462, 0.3337, 0.3564, 0.3649, 0.3468])
-
-        max_diff = numpy_cosine_similarity_distance(expected, images)
-        assert max_diff < 5e-3
-
-        pipe.unload_lora_weights()
-        release_memory(pipe)
-
     def test_sdxl_1_0_lora(self):
         generator = torch.Generator("cpu").manual_seed(0)
 

tests/models/transformers/test_models_transformer_aura_flow.py

@@ -26,7 +26,7 @@
 enable_full_determinism()
 
 
-class SD3TransformerTests(ModelTesterMixin, unittest.TestCase):
+class AuraFlowTransformerTests(ModelTesterMixin, unittest.TestCase):
     model_class = AuraFlowTransformer2DModel
     main_input_name = "hidden_states"
     # We override the items here because the transformer under consideration is small.
@@ -73,3 +73,7 @@ def prepare_init_args_and_inputs_for_common(self):
         }
         inputs_dict = self.dummy_input
         return init_dict, inputs_dict
+
+    @unittest.skip("AuraFlowTransformer2DModel uses its own dedicated attention processor. This test does not apply")
+    def test_set_attn_processor_for_determinism(self):
+        pass

tests/models/transformers/test_models_transformer_sd3.py

@@ -76,3 +76,7 @@ def prepare_init_args_and_inputs_for_common(self):
         }
         inputs_dict = self.dummy_input
         return init_dict, inputs_dict
+
+    @unittest.skip("SD3Transformer2DModel uses a dedicated attention processor. This test doesn't apply")
+    def test_set_attn_processor_for_determinism(self):
+        pass

tests/pipelines/aura_flow/test_pipeline_aura_flow.py

@@ -163,3 +163,7 @@ def test_fused_qkv_projections(self):
         assert np.allclose(
             original_image_slice, image_slice_disabled, atol=1e-2, rtol=1e-2
         ), "Original outputs should match when fused QKV projections are disabled."
+
+    @unittest.skip("xformers attention processor does not exist for AuraFlow")
+    def test_xformers_attention_forwardGenerator_pass(self):
+        pass

tests/pipelines/lumina/test_lumina_nextdit.py

@@ -119,6 +119,10 @@ def test_lumina_prompt_embeds(self):
         max_diff = np.abs(output_with_prompt - output_with_embeds).max()
         assert max_diff < 1e-4
 
+    @unittest.skip("xformers attention processor does not exist for Lumina")
+    def test_xformers_attention_forwardGenerator_pass(self):
+        pass
+
 
 @slow
 @require_torch_gpu

tests/pipelines/text_to_video_synthesis/test_text_to_video.py

@@ -20,12 +20,7 @@
 import torch
 from transformers import CLIPTextConfig, CLIPTextModel, CLIPTokenizer
 
-from diffusers import (
-    AutoencoderKL,
-    DDIMScheduler,
-    TextToVideoSDPipeline,
-    UNet3DConditionModel,
-)
+from diffusers import AutoencoderKL, DDIMScheduler, TextToVideoSDPipeline, UNet3DConditionModel
 from diffusers.utils import is_xformers_available
 from diffusers.utils.testing_utils import (
     enable_full_determinism,
@@ -64,7 +59,7 @@ class TextToVideoSDPipelineFastTests(PipelineTesterMixin, SDFunctionTesterMixin,
     def get_dummy_components(self):
         torch.manual_seed(0)
         unet = UNet3DConditionModel(
-            block_out_channels=(4, 8),
+            block_out_channels=(8, 8),
             layers_per_block=1,
             sample_size=32,
             in_channels=4,
@@ -134,10 +129,7 @@ def get_dummy_inputs(self, device, seed=0):
         return inputs
 
     def test_dict_tuple_outputs_equivalent(self):
-        expected_slice = None
-        if torch_device == "cpu":
-            expected_slice = np.array([0.4903, 0.5649, 0.5504, 0.5179, 0.4821, 0.5466, 0.4131, 0.5052, 0.5077])
-        return super().test_dict_tuple_outputs_equivalent(expected_slice=expected_slice)
+        return super().test_dict_tuple_outputs_equivalent()
 
     def test_text_to_video_default_case(self):
         device = "cpu"  # ensure determinism for the device-dependent torch.Generator
@@ -151,9 +143,8 @@ def test_text_to_video_default_case(self):
         frames = sd_pipe(**inputs).frames
 
         image_slice = frames[0][0][-3:, -3:, -1]
-
         assert frames[0][0].shape == (32, 32, 3)
-        expected_slice = np.array([0.7537, 0.1752, 0.6157, 0.5508, 0.4240, 0.4110, 0.4838, 0.5648, 0.5094])
+        expected_slice = np.array([0.8093, 0.2751, 0.6976, 0.5927, 0.4616, 0.4336, 0.5094, 0.5683, 0.4796])
 
         assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2