Add inversion equivalence test

tests/pipelines/stable_diffusion/test_stable_diffusion_pix2pix_zero.py

@@ -366,6 +366,29 @@ def test_stable_diffusion_pix2pix_inversion(self):
 
         assert np.abs(expected_slice - image_slice.cpu().numpy()).max() < 5e-2
 
+    def test_stable_diffusion_2_pix2pix_inversion(self):
+        pipe = StableDiffusionPix2PixZeroPipeline.from_pretrained(
+            "stabilityai/stable-diffusion-2-1", safety_checker=None, torch_dtype=torch.float16
+        )
+        pipe.inverse_scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+        pipe.inverse_scheduler = DDIMInverseScheduler.from_config(pipe.scheduler.config)
+
+        caption = "a photography of a cat with flowers"
+        pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+        pipe.enable_model_cpu_offload()
+        pipe.set_progress_bar_config(disable=None)
+
+        generator = torch.manual_seed(0)
+        output = pipe.invert(caption, image=self.raw_image, generator=generator, num_inference_steps=10)
+        inv_latents = output[0]
+
+        image_slice = inv_latents[0, -3:, -3:, -1].flatten()
+
+        assert inv_latents.shape == (1, 4, 64, 64)
+        expected_slice = np.array([0.7515, -0.2397,  0.4922, -0.9736, -0.7031,  0.4846, -1.0781,  1.1309, -0.6973])
+
+        assert np.abs(expected_slice - image_slice.cpu().numpy()).max() < 5e-2
+
     def test_stable_diffusion_pix2pix_full(self):
         # numpy array of https://huggingface.co/datasets/hf-internal-testing/diffusers-images/blob/main/pix2pix/dog.png
         expected_image = load_numpy(