keras-hub-nightly 0.16.1.dev202410080341__py3-none-any.whl → 0.16.1.dev202410100339__py3-none-any.whl

keras_hub/src/models/text_to_image.py

@@ -56,6 +56,11 @@ class TextToImage(Task):
         # Default compilation.
         self.compile()
 
+    @property
+    def support_negative_prompts(self):
+        """Whether the model supports `negative_prompts` key in `generate()`."""
+        return bool(True)
+
     @property
     def latent_shape(self):
         return tuple(self.backbone.latent_shape)
@@ -171,9 +176,26 @@ class TextToImage(Task):
         This function converts all inputs to tensors, adds a batch dimension if
         necessary, and returns a iterable "dataset like" object (either an
         actual `tf.data.Dataset` or a list with a single batch element).
+
+        The input format must be one of the following:
+        - A single string
+        - A list of strings
+        - A dict with "prompts" and/or "negative_prompts" keys
+        - A tf.data.Dataset with "prompts" and/or "negative_prompts" keys
+
+        The output will be a dict with "prompts" and/or "negative_prompts" keys.
         """
         if tf and isinstance(inputs, tf.data.Dataset):
-            return inputs.as_numpy_iterator(), False
+            _inputs = {
+                "prompts": inputs.map(
+                    lambda x: x["prompts"]
+                ).as_numpy_iterator()
+            }
+            if self.support_negative_prompts:
+                _inputs["negative_prompts"] = inputs.map(
+                    lambda x: x["negative_prompts"]
+                ).as_numpy_iterator()
+            return _inputs, False
 
         def normalize(x):
             if isinstance(x, str):
@@ -182,13 +204,24 @@ class TextToImage(Task):
                 return x[tf.newaxis], True
             return x, False
 
+        def get_dummy_prompts(x):
+            dummy_prompts = [""] * len(x)
+            if tf and isinstance(x, tf.Tensor):
+                return tf.convert_to_tensor(dummy_prompts)
+            else:
+                return dummy_prompts
+
         if isinstance(inputs, dict):
             for key in inputs:
                 inputs[key], input_is_scalar = normalize(inputs[key])
         else:
             inputs, input_is_scalar = normalize(inputs)
+            inputs = {"prompts": inputs}
 
-        return inputs, input_is_scalar
+        if self.support_negative_prompts and "negative_prompts" not in inputs:
+            inputs["negative_prompts"] = get_dummy_prompts(inputs["prompts"])
+
+        return [inputs], input_is_scalar
 
     def _normalize_generate_outputs(self, outputs, input_is_scalar):
         """Normalize user output from the generate function.
@@ -199,12 +232,11 @@ class TextToImage(Task):
         """
 
         def normalize(x):
-            outputs = ops.clip(ops.divide(ops.add(x, 1.0), 2.0), 0.0, 1.0)
+            outputs = ops.concatenate(x, axis=0)
+            outputs = ops.clip(ops.divide(ops.add(outputs, 1.0), 2.0), 0.0, 1.0)
             outputs = ops.cast(ops.round(ops.multiply(outputs, 255.0)), "uint8")
-            outputs = ops.convert_to_numpy(outputs)
-            if input_is_scalar:
-                outputs = outputs[0]
-            return outputs
+            outputs = ops.squeeze(outputs, 0) if input_is_scalar else outputs
+            return ops.convert_to_numpy(outputs)
 
         if isinstance(outputs[0], dict):
             normalized = {}
@@ -216,23 +248,40 @@ class TextToImage(Task):
     def generate(
         self,
         inputs,
-        negative_inputs,
         num_steps,
         guidance_scale,
         seed=None,
     ):
-        """Generate image based on the provided `inputs` and `negative_inputs`.
+        """Generate image based on the provided `inputs`.
+
+        Typically, `inputs` contains a text description (known as a prompt) used
+        to guide the image generation.
+
+        Some models support a `negative_prompts` key, which helps steer the
+        model away from generating certain styles and elements. To enable this,
+        pass `prompts` and `negative_prompts` as a dict:
+
+        ```python
+        text_to_image.generate(
+            {
+                "prompts": "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
+                "negative_prompts": "green color",
+            }
+        )
+        ```
 
         If `inputs` are a `tf.data.Dataset`, outputs will be generated
         "batch-by-batch" and concatenated. Otherwise, all inputs will be
         processed as batches.
 
         Args:
-            inputs: python data, tensor data, or a `tf.data.Dataset`.
-            negative_inputs: python data, tensor data, or a `tf.data.Dataset`.
-                Unlike `inputs`, these are used as negative inputs to guide the
-                generation. If not provided, it defaults to `""` for each input
-                in `inputs`.
+            inputs: python data, tensor data, or a `tf.data.Dataset`. The format
+                must be one of the following:
+                - A single string
+                - A list of strings
+                - A dict with "prompts" and/or "negative_prompts" keys
+                - A `tf.data.Dataset` with "prompts" and/or "negative_prompts"
+                    keys
             num_steps: int. The number of diffusion steps to take.
             guidance_scale: float. The classifier free guidance scale defined in
                 [Classifier-Free Diffusion Guidance](
@@ -251,32 +300,36 @@ class TextToImage(Task):
         generate_function = self.make_generate_function()
 
         def preprocess(x):
-            return self.preprocessor.generate_preprocess(x)
+            if self.preprocessor is not None:
+                return self.preprocessor.generate_preprocess(x)
+            else:
+                return x
+
+        def generate(x):
+            token_ids = x[0] if self.support_negative_prompts else x
+
+            # Initialize latents.
+            if isinstance(token_ids, dict):
+                arbitrary_key = list(token_ids.keys())[0]
+                batch_size = ops.shape(token_ids[arbitrary_key])[0]
+            else:
+                batch_size = ops.shape(token_ids)[0]
+            latent_shape = (batch_size,) + self.latent_shape[1:]
+            latents = random.normal(latent_shape, dtype="float32", seed=seed)
+
+            return generate_function(latents, x, num_steps, guidance_scale)
 
         # Normalize and preprocess inputs.
         inputs, input_is_scalar = self._normalize_generate_inputs(inputs)
-        if negative_inputs is None:
-            negative_inputs = [""] * len(inputs)
-        negative_inputs, _ = self._normalize_generate_inputs(negative_inputs)
-
-        if self.preprocessor is not None:
-            inputs = preprocess(inputs)
-            negative_inputs = preprocess(negative_inputs)
-        if isinstance(inputs, dict):
-            batch_size = len(inputs[list(inputs.keys())[0]])
+        if self.support_negative_prompts:
+            token_ids = [preprocess(x["prompts"]) for x in inputs]
+            negative_token_ids = [
+                preprocess(x["negative_prompts"]) for x in inputs
+            ]
+            inputs = [x for x in zip(token_ids, negative_token_ids)]
         else:
-            batch_size = len(inputs)
-
-        # Initialize random latents.
-        latent_shape = (batch_size,) + self.latent_shape[1:]
-        latents = random.normal(latent_shape, dtype="float32", seed=seed)
+            inputs = [preprocess(x["prompts"]) for x in inputs]
 
         # Text-to-image.
-        outputs = generate_function(
-            latents,
-            inputs,
-            negative_inputs,
-            num_steps,
-            guidance_scale,
-        )
+        outputs = [generate(x) for x in inputs]
         return self._normalize_generate_outputs(outputs, input_is_scalar)

keras_hub/src/tests/test_case.py

@@ -388,6 +388,8 @@ class TestCase(tf.test.TestCase, parameterized.TestCase):
         cls,
         init_kwargs,
         input_data,
+        atol=0.000001,
+        rtol=0.000001,
     ):
         """Save and load a model from disk and assert output is unchanged."""
         model = cls(**init_kwargs)
@@ -401,7 +403,7 @@ class TestCase(tf.test.TestCase, parameterized.TestCase):
 
         # Check that output matches.
         restored_output = restored_model(input_data)
-        self.assertAllClose(model_output, restored_output)
+        self.assertAllClose(model_output, restored_output, atol=atol, rtol=rtol)
 
     def run_backbone_test(
         self,

keras_hub/src/tokenizers/tokenizer.py

@@ -66,7 +66,7 @@ class Tokenizer(PreprocessingLayer):
     backbone_cls = None
 
     def __init__(self, *args, **kwargs):
-        self.config_name = kwargs.pop("config_name", TOKENIZER_CONFIG_FILE)
+        self.config_file = kwargs.pop("config_file", TOKENIZER_CONFIG_FILE)
         super().__init__(*args, **kwargs)
         self.file_assets = None
 
@@ -178,7 +178,7 @@ class Tokenizer(PreprocessingLayer):
         config = super().get_config()
         config.update(
             {
-                "config_name": self.config_name,
+                "config_file": self.config_file,
             }
         )
         return config
@@ -199,11 +199,11 @@ class Tokenizer(PreprocessingLayer):
     def load_preset_assets(self, preset):
         asset_path = None
         for asset in self.file_assets:
-            subdir = self.config_name.split(".")[0]
+            subdir = self.config_file.split(".")[0]
             preset_path = os.path.join(ASSET_DIR, subdir, asset)
             asset_path = get_file(preset, preset_path)
-        tokenizer_config_name = os.path.dirname(asset_path)
-        self.load_assets(tokenizer_config_name)
+        tokenizer_config_file = os.path.dirname(asset_path)
+        self.load_assets(tokenizer_config_file)
 
     @classproperty
     def presets(cls):
@@ -214,7 +214,7 @@ class Tokenizer(PreprocessingLayer):
     def from_preset(
         cls,
         preset,
-        config_name=TOKENIZER_CONFIG_FILE,
+        config_file=TOKENIZER_CONFIG_FILE,
         **kwargs,
     ):
         """Instantiate a `keras_hub.models.Tokenizer` from a model preset.
@@ -260,4 +260,4 @@ class Tokenizer(PreprocessingLayer):
         backbone_cls = loader.check_backbone_class()
         if cls.backbone_cls != backbone_cls:
             cls = find_subclass(preset, cls, backbone_cls)
-        return loader.load_tokenizer(cls, config_name, **kwargs)
+        return loader.load_tokenizer(cls, config_file, **kwargs)

keras_hub/src/utils/preset_utils.py

@@ -578,7 +578,7 @@ class PresetLoader:
         """Load the backbone model from the preset."""
         raise NotImplementedError
 
-    def load_tokenizer(self, cls, config_name=TOKENIZER_CONFIG_FILE, **kwargs):
+    def load_tokenizer(self, cls, config_file=TOKENIZER_CONFIG_FILE, **kwargs):
         """Load a tokenizer layer from the preset."""
         raise NotImplementedError
 
@@ -609,7 +609,7 @@ class PresetLoader:
         return cls(**kwargs)
 
     def load_preprocessor(
-        self, cls, config_name=PREPROCESSOR_CONFIG_FILE, **kwargs
+        self, cls, config_file=PREPROCESSOR_CONFIG_FILE, **kwargs
     ):
         """Load a prepocessor layer from the preset.
 
@@ -632,8 +632,8 @@ class KerasPresetLoader(PresetLoader):
             backbone.load_weights(get_file(self.preset, MODEL_WEIGHTS_FILE))
         return backbone
 
-    def load_tokenizer(self, cls, config_name=TOKENIZER_CONFIG_FILE, **kwargs):
-        tokenizer_config = load_json(self.preset, config_name)
+    def load_tokenizer(self, cls, config_file=TOKENIZER_CONFIG_FILE, **kwargs):
+        tokenizer_config = load_json(self.preset, config_file)
         tokenizer = load_serialized_object(tokenizer_config, **kwargs)
         if hasattr(tokenizer, "load_preset_assets"):
             tokenizer.load_preset_assets(self.preset)
@@ -678,13 +678,13 @@ class KerasPresetLoader(PresetLoader):
         return task
 
     def load_preprocessor(
-        self, cls, config_name=PREPROCESSOR_CONFIG_FILE, **kwargs
+        self, cls, config_file=PREPROCESSOR_CONFIG_FILE, **kwargs
     ):
         # If there is no `preprocessing.json` or it's for the wrong class,
         # delegate to the super class loader.
-        if not check_file_exists(self.preset, config_name):
+        if not check_file_exists(self.preset, config_file):
             return super().load_preprocessor(cls, **kwargs)
-        preprocessor_json = load_json(self.preset, config_name)
+        preprocessor_json = load_json(self.preset, config_file)
         if not issubclass(check_config_class(preprocessor_json), cls):
             return super().load_preprocessor(cls, **kwargs)
         # We found a `preprocessing.json` with a complete config for our class.

keras_hub/src/utils/timm/preset_loader.py

@@ -50,11 +50,10 @@ class TimmPresetLoader(PresetLoader):
 
     def load_image_converter(self, cls, **kwargs):
         pretrained_cfg = self.config.get("pretrained_cfg", None)
-        if not pretrained_cfg or "input_size" not in pretrained_cfg:
+        if not pretrained_cfg:
             return None
         # This assumes the same basic setup for all timm preprocessing, We may
         # need to extend this as we cover more model types.
-        input_size = pretrained_cfg["input_size"]
         mean = pretrained_cfg["mean"]
         std = pretrained_cfg["std"]
         scale = [1.0 / 255.0 / s for s in std]
@@ -63,7 +62,6 @@ class TimmPresetLoader(PresetLoader):
         if interpolation not in ("bilinear", "nearest", "bicubic"):
             interpolation = "bilinear"  # Unsupported interpolation type.
         return cls(
-            image_size=input_size[1:],
             scale=scale,
             offset=offset,
             interpolation=interpolation,

keras_hub/src/version_utils.py

@@ -1,7 +1,7 @@
 from keras_hub.src.api_export import keras_hub_export
 
 # Unique source of truth for the version number.
-__version__ = "0.16.1.dev202410080341"
+__version__ = "0.16.1.dev202410100339"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.16.1.dev202410080341.dist-info → keras_hub_nightly-0.16.1.dev202410100339.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: keras-hub-nightly
-Version: 0.16.1.dev202410080341
+Version: 0.16.1.dev202410100339
 Summary: Industry-strength Natural Language Processing extensions for Keras.
 Home-page: https://github.com/keras-team/keras-hub
 Author: Keras team

{keras_hub_nightly-0.16.1.dev202410080341.dist-info → keras_hub_nightly-0.16.1.dev202410100339.dist-info}/RECORD

@@ -1,15 +1,15 @@
 keras_hub/__init__.py,sha256=QGdXyHgYt6cMUAP1ebxwc6oR86dE0dkMxNy2eOCQtFo,855
 keras_hub/api/__init__.py,sha256=spMxsgqzjpeuC8rY4WP-2kAZ2qwwKRSbFwddXgUjqQE,524
 keras_hub/api/bounding_box/__init__.py,sha256=T8R_X7BPm0et1xaZq8565uJmid7dylsSFSj4V-rGuFQ,1097
-keras_hub/api/layers/__init__.py,sha256=XImD0tHdnDR1a7q3u-Pw-VRMASi9sDtrV6hr2beVYTw,2331
+keras_hub/api/layers/__init__.py,sha256=jQbYVdHrjC0PnJVa3myfJbAmRef9KGwrTgPDaTsWPJw,2439
 keras_hub/api/metrics/__init__.py,sha256=So8Ec-lOcTzn_UUMmAdzDm8RKkPu2dbRUm2px8gpUEI,381
-keras_hub/api/models/__init__.py,sha256=sMfVpa2N90cG7qjkwSEI_x3uCvZNwQqFbedn5wcUzbE,14311
+keras_hub/api/models/__init__.py,sha256=Z3GLSmrvds7-XDtkcB9gq_sNZ5zJ_3Rwl_xoZ-dTX14,14786
 keras_hub/api/samplers/__init__.py,sha256=n-_SEXxr2LNUzK2FqVFN7alsrkx1P_HOVTeLZKeGCdE,730
 keras_hub/api/tokenizers/__init__.py,sha256=_f-r_cyUM2fjBB7iO84ThOdqqsAxHNIewJ2EBDlM0cA,2524
 keras_hub/api/utils/__init__.py,sha256=Gp1E6gG-RtKQS3PBEQEOz9PQvXkXaJ0ySGMqZ7myN7A,215
 keras_hub/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/api_export.py,sha256=9pQZK27JObxWZ96QPLBp1OBsjWigh1iuV6RglPGMRk0,1499
-keras_hub/src/version_utils.py,sha256=ZcW3wGP8G9ckkrN4UDSpLre640ME6s_nJGCdK-nY_JI,222
+keras_hub/src/version_utils.py,sha256=ta3Ul-3W63rzG1EOq-JStAvR39K8vw23TKBmNmLl2MQ,222
 keras_hub/src/bounding_box/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/bounding_box/converters.py,sha256=a5po8DBm87oz2EXfi-0uEZHCMlCJPIb4-MaZIdYx3Dg,17865
 keras_hub/src/bounding_box/formats.py,sha256=YmskOz2BOSat7NaE__J9VfpSNGPJJR0znSzA4lp8MMI,3868
@@ -34,7 +34,7 @@ keras_hub/src/layers/modeling/transformer_encoder.py,sha256=howjIXH_vgBOKaXaIa7m
 keras_hub/src/layers/modeling/transformer_layer_utils.py,sha256=FuznrW33iG50B-VDN8R1RjuA5JG72yNMJ1TBgWLxR0E,3487
 keras_hub/src/layers/preprocessing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/preprocessing/audio_converter.py,sha256=YGh_kQw65a1Z6S5zzSNVP-ChyLYHq3-eOYpOS53xIN8,4156
-keras_hub/src/layers/preprocessing/image_converter.py,sha256=zlg6VKQWjKDCojJnI9VfK4Rt88QE29XjpDewZQNT8IE,10166
+keras_hub/src/layers/preprocessing/image_converter.py,sha256=j8SdL-pFOrWIGIV_HwlABUPhdcSOZXYhPRlvFCukAU8,10180
 keras_hub/src/layers/preprocessing/masked_lm_mask_generator.py,sha256=itxWq3FHYlR0I7jKarQlSKbSmRLl9ut_UTSP3ZDwP0A,8162
 keras_hub/src/layers/preprocessing/multi_segment_packer.py,sha256=ZNqnUFnc9Af122Q7T6YyUoXgIdU9AgIJfsvR1UrCjFU,12068
 keras_hub/src/layers/preprocessing/preprocessing_layer.py,sha256=WyX41b9Ev_YJ5uVQVOAqD0PQasMOPDoyDjl_PkzkAkE,687
@@ -57,15 +57,17 @@ keras_hub/src/models/image_classifier.py,sha256=yt6cjhPfqs8A_eWXBsXdXFzn-aRgH2rV
 keras_hub/src/models/image_classifier_preprocessor.py,sha256=YdewYfMPVHI7gdhbBI-zVcy4NSfg0bhiOHTmGEKoOYI,2668
 keras_hub/src/models/image_segmenter.py,sha256=C1bzIO59pG58iist5GLn_qnlotDpcAVxPV_8a68BkAc,2876
 keras_hub/src/models/image_segmenter_preprocessor.py,sha256=IMmVJWBc0VZ1-5jLmFmmwQ3q_oQnhIfCE9A6nS1ss8Q,3743
+keras_hub/src/models/image_to_image.py,sha256=z2TfFh9DiaEj9u6hEY8May3B0etxhptttg6Bx6bbopM,16452
+keras_hub/src/models/inpaint.py,sha256=8TTusRRS7ntPoAd0BsuhEZjedtaoljI4ZbgKQ_bnF34,20411
 keras_hub/src/models/masked_lm.py,sha256=uXO_dE_hILlOC9jNr6oK6IHi9IGUqLyNGvr6nMt8Rk0,3576
 keras_hub/src/models/masked_lm_preprocessor.py,sha256=g8vrnyYwqdnSw5xppROM1Gzo_jmMWKYZoQCsKdfrFKk,5656
-keras_hub/src/models/preprocessor.py,sha256=pJodz7KRVncvsC3o4qoKDYWP2J0a8E9CD6oVGYgJzIM,7970
+keras_hub/src/models/preprocessor.py,sha256=3CWLsMpQC77w7GzM3fU3Jf-G62ldJjufKyzPVvnGdeI,7970
 keras_hub/src/models/seq_2_seq_lm.py,sha256=w0gX-5YZjatfvAJmFAgSHyqS_BLqc8FF8DPLGK8mrgI,1864
 keras_hub/src/models/seq_2_seq_lm_preprocessor.py,sha256=HUHRbWRG5SF1pPpotGzBhXlrMh4pLFxgAoFk05FIrB4,9687
-keras_hub/src/models/task.py,sha256=2iapEFHvzyl0ASlH6yzQA2OHSr1jV1V-pLtagHdBncQ,14416
+keras_hub/src/models/task.py,sha256=VN-CClNw3EB5Byb7HyyI3CqaS140od7-dmQInmYFSKg,14414
 keras_hub/src/models/text_classifier.py,sha256=VBDvQUHTpJPqKp7A4VAtm35FOmJ3yMo0DW6GdX67xG0,4159
 keras_hub/src/models/text_classifier_preprocessor.py,sha256=EoWp-GHnaLnAKTdAzDmC-soAV92ATF3QozdubdV2WXI,4722
-keras_hub/src/models/text_to_image.py,sha256=N42l1W8YEUBHOdGiT4BQNqzTpgjB2O5dtLU5FbKpMy0,10792
+keras_hub/src/models/text_to_image.py,sha256=7s6rB1To46A7l9ItqRw3Pe4DGRm7YnqbHJ-RyNAlLPE,12973
 keras_hub/src/models/albert/__init__.py,sha256=rR6q_-8FujB1FXp6r4KOI7xi4gFjtAhQwXjp-MIhiyg,257
 keras_hub/src/models/albert/albert_backbone.py,sha256=4NQFo8lhv8rFiNIwQeZxxKxFwT3nKcCt36FUa6oPGok,10073
 keras_hub/src/models/albert/albert_masked_lm.py,sha256=jG6FttE_MAyBe8GzOEXMjEem3wo6UFGvxM3lRmXuS70,4126
@@ -207,10 +209,13 @@ keras_hub/src/models/mistral/mistral_layer_norm.py,sha256=nimMZ5CTPK8v9eflfrGuzq
 keras_hub/src/models/mistral/mistral_presets.py,sha256=gucgdaFAiU-vRDS1g9zWGHjbDF_jaCiljPibCF4yVqY,1329
 keras_hub/src/models/mistral/mistral_tokenizer.py,sha256=wyzR_Y2XwrDiBV3jIeBChSPiaOkVVaxFuLxMH2F6EYA,2005
 keras_hub/src/models/mistral/mistral_transformer_decoder.py,sha256=RDIIB3FhneHZP11tNUFQT9DcWawCMnrtVxtSvtnP3ts,9542
-keras_hub/src/models/mix_transformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+keras_hub/src/models/mix_transformer/__init__.py,sha256=neU-h7C0sXS6OmtS5NFJeJ1lF13OW3DaUlT6LXhl6vA,409
 keras_hub/src/models/mix_transformer/mix_transformer_backbone.py,sha256=B4hdhWHZ93lS937BGSSxovDKVXQZVuWrMbFwECFoWrg,6048
-keras_hub/src/models/mix_transformer/mix_transformer_classifier.py,sha256=uXO2-GzI_25TdlXe8O8qvnM7tryadfetVDW3yJLGfiI,348
-keras_hub/src/models/mix_transformer/mix_transformer_layers.py,sha256=SzyJJhuyESlsCgndmZNYuuF0Ogb1FKoYkSfDJnThgT0,9538
+keras_hub/src/models/mix_transformer/mix_transformer_classifier.py,sha256=pVfbbTNuiZRFElCGLyNO3gknNGnut-6-L-zAVB4Nb5w,531
+keras_hub/src/models/mix_transformer/mix_transformer_classifier_preprocessor.py,sha256=lSUuMAJiyWDVH0AVjG2y684bU3msxI3_UTa_xWyLLKQ,570
+keras_hub/src/models/mix_transformer/mix_transformer_image_converter.py,sha256=WG2LjuagCxSYXkFgqd4bHyUoMLFCzTj9QjJBoptW6WM,323
+keras_hub/src/models/mix_transformer/mix_transformer_layers.py,sha256=9AbA4kCJkjeV7fAwbRns8VGn0l1pgQ3CqFPjY-99VGA,9695
+keras_hub/src/models/mix_transformer/mix_transformer_presets.py,sha256=rWrjAAwc9Kmo0c66CNh5cuIpySzqqLKj_VI6hlI9d44,5116
 keras_hub/src/models/mobilenet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/models/mobilenet/mobilenet_backbone.py,sha256=nlXdMqcj18iahy60aew4ON79EHUEuNIgvKY9dToH284,18191
 keras_hub/src/models/mobilenet/mobilenet_image_classifier.py,sha256=l5jo99I0fLlbwLub5jHw07CjC-NnmuV-ySJwXGI20Ek,351
@@ -271,10 +276,12 @@ keras_hub/src/models/sam/sam_prompt_encoder.py,sha256=2foB7900QbzQfZjBo335XYsdjm
 keras_hub/src/models/sam/sam_transformer.py,sha256=L2bdxdc2RUF1juRZ0F0Z6r0gTva1sUwEdjItJmKKf6w,5730
 keras_hub/src/models/stable_diffusion_3/__init__.py,sha256=ZKYQuaRObyhKq8GVAHmoRvlXp6FpU8ChvutVCHyXKuc,343
 keras_hub/src/models/stable_diffusion_3/flow_match_euler_discrete_scheduler.py,sha256=vtVhieAv277mAiZj7Kvvqg_Ba7klfQxZVk4PPxNNQ0s,3062
-keras_hub/src/models/stable_diffusion_3/mmdit.py,sha256=ntmxjDJtZbHDGVPPAnasVZyoOTp5bbMPhxM30SYmpoQ,25711
-keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_backbone.py,sha256=D-U5T6UYKzraHLAgMa-LLcd40ZmX_5rmlybawT4ooHY,21398
-keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_presets.py,sha256=sBGVRFd-bYxcqydydOB70XpOtpTt6AVrTR3LV-LBFXY,662
-keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_text_to_image.py,sha256=8nP3ejDOd1hqjYXJzbri62PgtclxGydw-8bw-qHIPdc,4414
+keras_hub/src/models/stable_diffusion_3/mmdit.py,sha256=ByFot4_I1Z6woOBYvPcbkUtYXWn-dPwgg-4het5vrH4,30615
+keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_backbone.py,sha256=QuggvAy1yvtIXFcwyXOmE_aUdhLcCEUw4FnTuqekys0,22497
+keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_image_to_image.py,sha256=6_IXkxAv588lAKEasJrXgCjQePSXs-54XrvVIlYOT60,5483
+keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_inpaint.py,sha256=tKVAQVbKOt3lWkWsQLKN9KK3WYem0-u5fonq2uBAPrc,6367
+keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_presets.py,sha256=QSDCse8IhEwAWz_lHjAr2N8ygLaJ4ls3uNwvwjJTp5w,662
+keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_text_to_image.py,sha256=pQOC7xMJfJHZxZRiYFtjrbjx0GXb94cNyOr9NELoXo8,4488
 keras_hub/src/models/stable_diffusion_3/stable_diffusion_3_text_to_image_preprocessor.py,sha256=TB0KESt5dnFYiS292PbzB0LdiH23AD6aTSTGmQEuzGM,2742
 keras_hub/src/models/stable_diffusion_3/t5_encoder.py,sha256=oV7P1uwCKdGiD93zXq7kmqX0elMZQU4UvBa8wg6P1hs,5113
 keras_hub/src/models/t5/__init__.py,sha256=OWyoUeDY3v4DnO8Ry02DWV1bNSVGcC89PF9oCftyi1s,233
@@ -325,20 +332,20 @@ keras_hub/src/samplers/serialization.py,sha256=K6FC4AY1sfOLLIk2k4G783XWnQ_Rk3z1Q
 keras_hub/src/samplers/top_k_sampler.py,sha256=WSyrhmOCan55X2JYAnNWE88rkx66sXqdoerl87nOrDQ,2250
 keras_hub/src/samplers/top_p_sampler.py,sha256=9r29WdqBlrW_2TBma6QqkRps2Uit4a6iZPmq1Gsiuko,3400
 keras_hub/src/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-keras_hub/src/tests/test_case.py,sha256=pgjT5CkkkX4BTNfaDD6i-YChO6Ig3But66Ls4RxEymw,25937
+keras_hub/src/tests/test_case.py,sha256=9-yV87k508ciVOJUBiypd8HmnDTHVtWU2m_RbOHMv5Q,26005
 keras_hub/src/tokenizers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/tokenizers/byte_pair_tokenizer.py,sha256=fGFp3WgPNYGTztpSGMl0kKFjn1bCeZB71lSJfT1eqEE,24052
 keras_hub/src/tokenizers/byte_tokenizer.py,sha256=vjgrTT8FdtZVAlr0mU13alzADcUhtMrzgOs4lYeHvAQ,10648
 keras_hub/src/tokenizers/sentence_piece_tokenizer.py,sha256=_PaVn4re3AwBkHylJWsvdvOCCYjOnFXLZmj-V34KehU,9562
 keras_hub/src/tokenizers/sentence_piece_tokenizer_trainer.py,sha256=8X_IN-hPDiUETGrSX3wPzFnip73xTYcN6FhLNIwfy-Y,4834
-keras_hub/src/tokenizers/tokenizer.py,sha256=xiT8efGyNmTgsbi6JoJzKUoGg3rWbHjykhfW5mnDbbw,9722
+keras_hub/src/tokenizers/tokenizer.py,sha256=v0Ka5ayrBwpsGBlkIadXK-b4RsMTbhV6BZrvKullbxY,9722
 keras_hub/src/tokenizers/unicode_codepoint_tokenizer.py,sha256=efyjXjUyUCsnh97_kPFq1z2QZENiZSdV0voZytLBffg,13531
 keras_hub/src/tokenizers/word_piece_tokenizer.py,sha256=vP6AZgbzsRiuPCt3W_n94nsF7XiERnagWcH_rqJHtVU,19943
 keras_hub/src/tokenizers/word_piece_tokenizer_trainer.py,sha256=xUhc9EMswarzghNfrDLUFYQBExZOQxbMlfKp9G6A63k,6549
 keras_hub/src/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/keras_utils.py,sha256=lrZuC8HL2lmQfbHaS_t1JUyJann_ji2iTYE0Fzos8PU,1969
 keras_hub/src/utils/pipeline_model.py,sha256=33-0vIB9KGYh2mRtyjHxBPvgGZHDusRcRy-xjki3_gg,9024
-keras_hub/src/utils/preset_utils.py,sha256=O7SbhcJJAoPeMhAF77ppG6XkIAIqBqAQVhKoE-Yt61c,30119
+keras_hub/src/utils/preset_utils.py,sha256=w45mluy4bhPPWB68waWpXFQ4MAKvSXS6llVw4rAE70s,30119
 keras_hub/src/utils/python_utils.py,sha256=N8nWeO3san4YnGkffRXG3Ix7VEIMTKSN21FX5TuL7G8,202
 keras_hub/src/utils/tensor_utils.py,sha256=JipeJUDnnvLuT-ToVQC0t9dmSzebwPG6XiZgEwGEGI4,14646
 keras_hub/src/utils/imagenet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -346,7 +353,7 @@ keras_hub/src/utils/imagenet/imagenet_utils.py,sha256=MvIvv1WJo51ZXBxy4S7t_DsN3Z
 keras_hub/src/utils/timm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/timm/convert_densenet.py,sha256=V-GRjWuDnlh3b1EMxqahwZ3GMwSgOa3v0HOfb2ZZ-d0,3342
 keras_hub/src/utils/timm/convert_resnet.py,sha256=ee8eTml0ffJKE8avzGoLFcpjPF63DsvoIUArAGa8Ngg,5832
-keras_hub/src/utils/timm/preset_loader.py,sha256=SbDqy2nr54_Y7bwe4sICQ8n-kHnw0PtvNI52tgrH170,3095
+keras_hub/src/utils/timm/preset_loader.py,sha256=CW-yNXvp3IExK3xuHKjYqbLdBVUST2kSsLmWxSs0i5c,2968
 keras_hub/src/utils/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/transformers/convert_albert.py,sha256=VdKclZpCxtDWq3UbUUQZf4fR9DJK_JYZ73B4O_G9skg,7695
 keras_hub/src/utils/transformers/convert_bart.py,sha256=Tk4h9Md9rwN5wjQbGIVrC7qzDpF8kI8qm-FKL8HlUok,14411
@@ -359,7 +366,7 @@ keras_hub/src/utils/transformers/convert_mistral.py,sha256=kVhN9h1ZFVhwkNW8p3wnS
 keras_hub/src/utils/transformers/convert_pali_gemma.py,sha256=B1leeDw96Yvu81hYumf66hIid07k5NLqoeWAJgPnaLs,10649
 keras_hub/src/utils/transformers/preset_loader.py,sha256=GS44hZUuGQCtzsyn8z44ZpHdftd3DFemwV2hx2bQa-U,2738
 keras_hub/src/utils/transformers/safetensor_utils.py,sha256=rPK-Uw1CG0DX0d_UAD-r2cG9fw8GI8bvAlrcXfQ9g4c,3323
-keras_hub_nightly-0.16.1.dev202410080341.dist-info/METADATA,sha256=SrlKiCjbDmXdTPsxSP6_NNTb-RKCwlNldhrxmphg_5Y,7458
-keras_hub_nightly-0.16.1.dev202410080341.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-keras_hub_nightly-0.16.1.dev202410080341.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.16.1.dev202410080341.dist-info/RECORD,,
+keras_hub_nightly-0.16.1.dev202410100339.dist-info/METADATA,sha256=Q1QCPvLIZpKSgKKhzvHH4Qng8vWrQihbFRVWk85Pjqs,7458
+keras_hub_nightly-0.16.1.dev202410100339.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+keras_hub_nightly-0.16.1.dev202410100339.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.16.1.dev202410100339.dist-info/RECORD,,