diff --git a/tests/models/transformers/test_models_transformer_hunyuan_1_5.py b/tests/models/transformers/test_models_transformer_hunyuan_1_5.py
new file mode 100644
index 000000000000..021fcdc9cfbf
--- /dev/null
+++ b/tests/models/transformers/test_models_transformer_hunyuan_1_5.py
@@ -0,0 +1,100 @@
+# Copyright 2025 HuggingFace Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import unittest
+
+import torch
+
+from diffusers import HunyuanVideo15Transformer3DModel
+
+from ...testing_utils import enable_full_determinism, torch_device
+from ..test_modeling_common import ModelTesterMixin
+
+
+enable_full_determinism()
+
+
+class HunyuanVideo15Transformer3DTests(ModelTesterMixin, unittest.TestCase):
+    model_class = HunyuanVideo15Transformer3DModel
+    main_input_name = "hidden_states"
+    uses_custom_attn_processor = True
+
+    text_embed_dim = 16
+    text_embed_2_dim = 8
+    image_embed_dim = 12
+
+    @property
+    def dummy_input(self):
+        batch_size = 1
+        num_channels = 4
+        num_frames = 1
+        height = 8
+        width = 8
+        sequence_length = 6
+        sequence_length_2 = 4
+        image_sequence_length = 3
+
+        hidden_states = torch.randn((batch_size, num_channels, num_frames, height, width)).to(torch_device)
+        timestep = torch.tensor([1.0]).to(torch_device)
+        encoder_hidden_states = torch.randn((batch_size, sequence_length, self.text_embed_dim), device=torch_device)
+        encoder_hidden_states_2 = torch.randn(
+            (batch_size, sequence_length_2, self.text_embed_2_dim), device=torch_device
+        )
+        encoder_attention_mask = torch.ones((batch_size, sequence_length), device=torch_device)
+        encoder_attention_mask_2 = torch.ones((batch_size, sequence_length_2), device=torch_device)
+        # All zeros for inducing T2V path in the model.
+        image_embeds = torch.zeros((batch_size, image_sequence_length, self.image_embed_dim), device=torch_device)
+
+        return {
+            "hidden_states": hidden_states,
+            "timestep": timestep,
+            "encoder_hidden_states": encoder_hidden_states,
+            "encoder_attention_mask": encoder_attention_mask,
+            "encoder_hidden_states_2": encoder_hidden_states_2,
+            "encoder_attention_mask_2": encoder_attention_mask_2,
+            "image_embeds": image_embeds,
+        }
+
+    @property
+    def input_shape(self):
+        return (4, 1, 8, 8)
+
+    @property
+    def output_shape(self):
+        return (4, 1, 8, 8)
+
+    def prepare_init_args_and_inputs_for_common(self):
+        init_dict = {
+            "in_channels": 4,
+            "out_channels": 4,
+            "num_attention_heads": 2,
+            "attention_head_dim": 8,
+            "num_layers": 2,
+            "num_refiner_layers": 1,
+            "mlp_ratio": 2.0,
+            "patch_size": 1,
+            "patch_size_t": 1,
+            "text_embed_dim": self.text_embed_dim,
+            "text_embed_2_dim": self.text_embed_2_dim,
+            "image_embed_dim": self.image_embed_dim,
+            "rope_axes_dim": (2, 2, 4),
+            "target_size": 16,
+            "task_type": "t2v",
+        }
+        inputs_dict = self.dummy_input
+        return init_dict, inputs_dict
+
+    def test_gradient_checkpointing_is_applied(self):
+        expected_set = {"HunyuanVideo15Transformer3DModel"}
+        super().test_gradient_checkpointing_is_applied(expected_set=expected_set)
diff --git a/tests/pipelines/hunyuan_video1_5/__init__.py b/tests/pipelines/hunyuan_video1_5/__init__.py
new file mode 100644
index 000000000000..8fb044d9cf83
--- /dev/null
+++ b/tests/pipelines/hunyuan_video1_5/__init__.py
@@ -0,0 +1 @@
+# Copyright 2025 The HuggingFace Team.
diff --git a/tests/pipelines/hunyuan_video1_5/test_hunyuan_1_5.py b/tests/pipelines/hunyuan_video1_5/test_hunyuan_1_5.py
new file mode 100644
index 000000000000..2d8cc8f257f6
--- /dev/null
+++ b/tests/pipelines/hunyuan_video1_5/test_hunyuan_1_5.py
@@ -0,0 +1,195 @@
+# Copyright 2025 The HuggingFace Team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import unittest
+
+import torch
+from transformers import ByT5Tokenizer, Qwen2_5_VLTextConfig, Qwen2_5_VLTextModel, Qwen2Tokenizer, T5EncoderModel
+
+from diffusers import (
+    AutoencoderKLHunyuanVideo15,
+    FlowMatchEulerDiscreteScheduler,
+    HunyuanVideo15Pipeline,
+    HunyuanVideo15Transformer3DModel,
+)
+from diffusers.guiders import ClassifierFreeGuidance
+
+from ...testing_utils import enable_full_determinism
+from ..test_pipelines_common import PipelineTesterMixin
+
+
+enable_full_determinism()
+
+
+class HunyuanVideo15PipelineFastTests(PipelineTesterMixin, unittest.TestCase):
+    pipeline_class = HunyuanVideo15Pipeline
+    params = frozenset(
+        [
+            "prompt",
+            "negative_prompt",
+            "height",
+            "width",
+            "prompt_embeds",
+            "prompt_embeds_mask",
+            "negative_prompt_embeds",
+            "negative_prompt_embeds_mask",
+            "prompt_embeds_2",
+            "prompt_embeds_mask_2",
+            "negative_prompt_embeds_2",
+            "negative_prompt_embeds_mask_2",
+        ]
+    )
+    batch_params = ["prompt", "negative_prompt"]
+    required_optional_params = frozenset(
+        [
+            "num_inference_steps",
+            "generator",
+            "latents",
+            "return_dict"
+        ]
+    )
+    test_attention_slicing = False
+    test_xformers_attention = False
+    test_layerwise_casting = True
+    test_group_offloading = False
+    supports_dduf = False
+
+    def get_dummy_components(self, num_layers: int = 1):
+        torch.manual_seed(0)
+        transformer = HunyuanVideo15Transformer3DModel(
+            in_channels=9,
+            out_channels=4,
+            num_attention_heads=2,
+            attention_head_dim=8,
+            num_layers=num_layers,
+            num_refiner_layers=1,
+            mlp_ratio=2.0,
+            patch_size=1,
+            patch_size_t=1,
+            text_embed_dim=16,
+            text_embed_2_dim=32,
+            image_embed_dim=12,
+            rope_axes_dim=(2, 2, 4),
+            target_size=16,
+            task_type="t2v",
+        )
+
+        torch.manual_seed(0)
+        vae = AutoencoderKLHunyuanVideo15(
+            in_channels=3,
+            out_channels=3,
+            latent_channels=4,
+            block_out_channels=(16, 16),
+            layers_per_block=1,
+            spatial_compression_ratio=4,
+            temporal_compression_ratio=2,
+            downsample_match_channel=False,
+            upsample_match_channel=False,
+        )
+
+        torch.manual_seed(0)
+        scheduler = FlowMatchEulerDiscreteScheduler(shift=7.0)
+
+        torch.manual_seed(0)
+        qwen_config = Qwen2_5_VLTextConfig(
+            **{
+                "hidden_size": 16,
+                "intermediate_size": 16,
+                "num_hidden_layers": 2,
+                "num_attention_heads": 2,
+                "num_key_value_heads": 2,
+                "rope_scaling": {
+                    "mrope_section": [1, 1, 2],
+                    "rope_type": "default",
+                    "type": "default",
+                },
+                "rope_theta": 1000000.0,
+            }
+        )
+        text_encoder = Qwen2_5_VLTextModel(qwen_config)
+        tokenizer = Qwen2Tokenizer.from_pretrained("hf-internal-testing/tiny-random-Qwen2VLForConditionalGeneration")
+
+        torch.manual_seed(0)
+        text_encoder_2 = T5EncoderModel.from_pretrained("hf-internal-testing/tiny-random-t5")
+        tokenizer_2 = ByT5Tokenizer()
+
+        guider = ClassifierFreeGuidance(guidance_scale=1.0)
+
+        components = {
+            "transformer": transformer.eval(),
+            "vae": vae.eval(),
+            "scheduler": scheduler,
+            "text_encoder": text_encoder.eval(),
+            "text_encoder_2": text_encoder_2.eval(),
+            "tokenizer": tokenizer,
+            "tokenizer_2": tokenizer_2,
+            "guider": guider,
+        }
+        return components
+
+    def get_dummy_inputs(self, device, seed=0):
+        if str(device).startswith("mps"):
+            generator = torch.manual_seed(seed)
+        else:
+            generator = torch.Generator(device=device).manual_seed(seed)
+
+        inputs = {
+            "prompt": "monkey",
+            "generator": generator,
+            "num_inference_steps": 2,
+            "height": 16,
+            "width": 16,
+            "num_frames": 9,
+            "output_type": "pt",
+        }
+        return inputs
+
+    def test_inference(self):
+        device = "cpu"
+
+        components = self.get_dummy_components()
+        pipe = self.pipeline_class(**components)
+        pipe.to(device)
+        pipe.set_progress_bar_config(disable=None)
+
+        inputs = self.get_dummy_inputs(device)
+        result = pipe(**inputs)
+        video = result.frames
+
+        generated_video = video[0]
+        self.assertEqual(generated_video.shape, (9, 3, 16, 16))
+        generated_slice = generated_video.flatten()
+        generated_slice = torch.cat([generated_slice[:8], generated_slice[-8:]])
+
+        # fmt: off
+        expected_slice = torch.tensor([0.4296, 0.5549, 0.3088, 0.9115, 0.5049, 0.7926, 0.5549, 0.8618, 0.5091, 0.5075, 0.7117, 0.5292, 0.7053, 0.4864, 0.5206, 0.3878])
+        # fmt: on
+
+        self.assertTrue(
+            torch.abs(generated_slice - expected_slice).max() < 1e-3,
+            f"output_slice: {generated_slice}, expected_slice: {expected_slice}",
+        )
+
+    @unittest.skip("TODO: Test not supported for now because needs to be adjusted to work with guiders.")
+    def test_encode_prompt_works_in_isolation(self):
+        pass
+
+    @unittest.skip("Needs to be revisited.")
+    def test_inference_batch_consistent(self):
+        super().test_inference_batch_consistent()
+
+    @unittest.skip("Needs to be revisited.")
+    def test_inference_batch_single_identical(self):
+        super().test_inference_batch_single_identical()
+