[Local loading] Correct bug with local files only (#4318)

* [Local loading] Correct bug with local files only

* file not found error

* fix

* finish

src/diffusers/pipelines/pipeline_utils.py

@@ -1474,11 +1474,25 @@ def download(cls, pretrained_model_name, **kwargs) -> Union[str, os.PathLike]:
                 user_agent=user_agent,
             )
 
-            if pipeline_class._load_connected_pipes:
+            # retrieve pipeline class from local file
+            cls_name = cls.load_config(os.path.join(cached_folder, "model_index.json")).get("_class_name", None)
+            pipeline_class = getattr(diffusers, cls_name, None)
+
+            if pipeline_class is not None and pipeline_class._load_connected_pipes:
                 modelcard = ModelCard.load(os.path.join(cached_folder, "README.md"))
                 connected_pipes = sum([getattr(modelcard.data, k, []) for k in CONNECTED_PIPES_KEYS], [])
                 for connected_pipe_repo_id in connected_pipes:
-                    DiffusionPipeline.download(connected_pipe_repo_id)
+                    download_kwargs = {
+                        "cache_dir": cache_dir,
+                        "resume_download": resume_download,
+                        "force_download": force_download,
+                        "proxies": proxies,
+                        "local_files_only": local_files_only,
+                        "use_auth_token": use_auth_token,
+                        "variant": variant,
+                        "use_safetensors": use_safetensors,
+                    }
+                    DiffusionPipeline.download(connected_pipe_repo_id, **download_kwargs)
 
             return cached_folder
 

tests/models/test_lora_layers.py

@@ -563,10 +563,10 @@ def get_dummy_components(self):
             projection_dim=32,
         )
         text_encoder = CLIPTextModel(text_encoder_config)
-        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         text_encoder_2 = CLIPTextModelWithProjection(text_encoder_config)
-        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         unet_lora_attn_procs, unet_lora_layers = create_unet_lora_layers(unet)
         text_encoder_one_lora_layers = create_text_encoder_lora_layers(text_encoder)

tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl.py

@@ -100,10 +100,10 @@ def get_dummy_components(self):
             projection_dim=32,
         )
         text_encoder = CLIPTextModel(text_encoder_config)
-        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         text_encoder_2 = CLIPTextModelWithProjection(text_encoder_config)
-        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         components = {
             "unet": unet,

tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_img2img.py

@@ -100,10 +100,10 @@ def get_dummy_components(self, skip_first_text_encoder=False):
             projection_dim=32,
         )
         text_encoder = CLIPTextModel(text_encoder_config)
-        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         text_encoder_2 = CLIPTextModelWithProjection(text_encoder_config)
-        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         components = {
             "unet": unet,

tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_inpaint.py

@@ -102,10 +102,10 @@ def get_dummy_components(self, skip_first_text_encoder=False):
             projection_dim=32,
         )
         text_encoder = CLIPTextModel(text_encoder_config)
-        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         text_encoder_2 = CLIPTextModelWithProjection(text_encoder_config)
-        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         components = {
             "unet": unet,

tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_instruction_pix2pix.py

@@ -105,10 +105,10 @@ def get_dummy_components(self):
             projection_dim=32,
         )
         text_encoder = CLIPTextModel(text_encoder_config)
-        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         text_encoder_2 = CLIPTextModelWithProjection(text_encoder_config)
-        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip", local_files_only=True)
+        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
 
         components = {
             "unet": unet,

tests/pipelines/test_pipelines.py

@@ -374,15 +374,15 @@ def test_cached_files_are_used_when_no_internet(self):
         response_mock.json.return_value = {}
 
         # Download this model to make sure it's in the cache.
-        orig_pipe = StableDiffusionPipeline.from_pretrained(
+        orig_pipe = DiffusionPipeline.from_pretrained(
             "hf-internal-testing/tiny-stable-diffusion-torch", safety_checker=None
         )
         orig_comps = {k: v for k, v in orig_pipe.components.items() if hasattr(v, "parameters")}
 
         # Under the mock environment we get a 500 error when trying to reach the model.
         with mock.patch("requests.request", return_value=response_mock):
             # Download this model to make sure it's in the cache.
-            pipe = StableDiffusionPipeline.from_pretrained(
+            pipe = DiffusionPipeline.from_pretrained(
                 "hf-internal-testing/tiny-stable-diffusion-torch", safety_checker=None
             )
             comps = {k: v for k, v in pipe.components.items() if hasattr(v, "parameters")}
@@ -392,6 +392,42 @@ def test_cached_files_are_used_when_no_internet(self):
                 if p1.data.ne(p2.data).sum() > 0:
                     assert False, "Parameters not the same!"
 
+    def test_local_files_only_are_used_when_no_internet(self):
+        # A mock response for an HTTP head request to emulate server down
+        response_mock = mock.Mock()
+        response_mock.status_code = 500
+        response_mock.headers = {}
+        response_mock.raise_for_status.side_effect = HTTPError
+        response_mock.json.return_value = {}
+
+        # first check that with local files only the pipeline can only be used if cached
+        with self.assertRaises(FileNotFoundError):
+            with tempfile.TemporaryDirectory() as tmpdirname:
+                orig_pipe = DiffusionPipeline.from_pretrained(
+                    "hf-internal-testing/tiny-stable-diffusion-torch", local_files_only=True, cache_dir=tmpdirname
+                )
+
+        # now download
+        orig_pipe = DiffusionPipeline.download("hf-internal-testing/tiny-stable-diffusion-torch")
+
+        # make sure it can be loaded with local_files_only
+        orig_pipe = DiffusionPipeline.from_pretrained(
+            "hf-internal-testing/tiny-stable-diffusion-torch", local_files_only=True
+        )
+        orig_comps = {k: v for k, v in orig_pipe.components.items() if hasattr(v, "parameters")}
+
+        # Under the mock environment we get a 500 error when trying to connect to the internet.
+        # Make sure it works local_files_only only works here!
+        with mock.patch("requests.request", return_value=response_mock):
+            # Download this model to make sure it's in the cache.
+            pipe = DiffusionPipeline.from_pretrained("hf-internal-testing/tiny-stable-diffusion-torch")
+            comps = {k: v for k, v in pipe.components.items() if hasattr(v, "parameters")}
+
+        for m1, m2 in zip(orig_comps.values(), comps.values()):
+            for p1, p2 in zip(m1.parameters(), m2.parameters()):
+                if p1.data.ne(p2.data).sum() > 0:
+                    assert False, "Parameters not the same!"
+
     def test_download_from_variant_folder(self):
         for safe_avail in [False, True]:
             import diffusers

tests/pipelines/test_pipelines_common.py

@@ -387,7 +387,7 @@ def _test_inference_batch_consistent(
                         batched_inputs[name] = [value[: len_prompt // i] for i in range(1, batch_size + 1)]
 
                         # make last batch super long
-                        batched_inputs[name][-1] = 2000 * "very long"
+                        batched_inputs[name][-1] = 100 * "very long"
                     # or else we have images
                     else:
                         batched_inputs[name] = batch_size * [value]
@@ -462,7 +462,7 @@ def _test_inference_batch_single_identical(
                     batched_inputs[name] = [value[: len_prompt // i] for i in range(1, batch_size + 1)]
 
                     # make last batch super long
-                    batched_inputs[name][-1] = 2000 * "very long"
+                    batched_inputs[name][-1] = 100 * "very long"
                 # or else we have images
                 else:
                     batched_inputs[name] = batch_size * [value]