InvokeAI 4.2.9.dev8__tar.gz → 4.2.9.dev10__tar.gz

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/InvokeAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.2.9.dev8
+Version: 4.2.9.dev10
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/InvokeAI.egg-info/SOURCES.txt

@@ -403,11 +403,11 @@ invokeai/frontend/install/__init__.py
 invokeai/frontend/install/import_images.py
 invokeai/frontend/web/__init__.py
 invokeai/frontend/web/dist/index.html
-invokeai/frontend/web/dist/assets/App-B1xXrt8x.js
 invokeai/frontend/web/dist/assets/App-DEu4J2pT.css
+invokeai/frontend/web/dist/assets/App-DUFQH-Kw.js
 invokeai/frontend/web/dist/assets/ThemeLocaleProvider-B2NxUfIp.css
-invokeai/frontend/web/dist/assets/ThemeLocaleProvider-BSRQyfxR.js
-invokeai/frontend/web/dist/assets/index-4VBs_C-Q.js
+invokeai/frontend/web/dist/assets/ThemeLocaleProvider-Dc0lAavD.js
+invokeai/frontend/web/dist/assets/index-DK9y4o4h.js
 invokeai/frontend/web/dist/assets/inter-cyrillic-ext-wght-normal-B2xhLi22.woff2
 invokeai/frontend/web/dist/assets/inter-cyrillic-wght-normal-CMZtQduZ.woff2
 invokeai/frontend/web/dist/assets/inter-greek-ext-wght-normal-CGAr0uHJ.woff2

InvokeAI-4.2.9.dev10/InvokeAI.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+invokeai-web = invokeai.app.run_app:run_app

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.2.9.dev8
+Version: 4.2.9.dev10
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/app/invocations/fields.py

@@ -45,11 +45,13 @@ class UIType(str, Enum, metaclass=MetaEnum):
     SDXLRefinerModel = "SDXLRefinerModelField"
     ONNXModel = "ONNXModelField"
     VAEModel = "VAEModelField"
+    FluxVAEModel = "FluxVAEModelField"
     LoRAModel = "LoRAModelField"
     ControlNetModel = "ControlNetModelField"
     IPAdapterModel = "IPAdapterModelField"
     T2IAdapterModel = "T2IAdapterModelField"
     T5EncoderModel = "T5EncoderModelField"
+    CLIPEmbedModel = "CLIPEmbedModelField"
     SpandrelImageToImageModel = "SpandrelImageToImageModelField"
     # endregion
 
@@ -128,6 +130,7 @@ class FieldDescriptions:
     noise = "Noise tensor"
     clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
     t5_encoder = "T5 tokenizer and text encoder"
+    clip_embed_model = "CLIP Embed loader"
     unet = "UNet (scheduler, LoRAs)"
     transformer = "Transformer"
     vae = "VAE"

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/app/invocations/flux_text_encoder.py

@@ -40,7 +40,10 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> FluxConditioningOutput:
-        t5_embeddings, clip_embeddings = self._encode_prompt(context)
+        # Note: The T5 and CLIP encoding are done in separate functions to ensure that all model references are locally
+        # scoped. This ensures that the T5 model can be freed and gc'd before loading the CLIP model (if necessary).
+        t5_embeddings = self._t5_encode(context)
+        clip_embeddings = self._clip_encode(context)
         conditioning_data = ConditioningFieldData(
             conditionings=[FLUXConditioningInfo(clip_embeds=clip_embeddings, t5_embeds=t5_embeddings)]
         )
@@ -48,12 +51,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
         conditioning_name = context.conditioning.save(conditioning_data)
         return FluxConditioningOutput.build(conditioning_name)
 
-    def _encode_prompt(self, context: InvocationContext) -> tuple[torch.Tensor, torch.Tensor]:
-        # Load CLIP.
-        clip_tokenizer_info = context.models.load(self.clip.tokenizer)
-        clip_text_encoder_info = context.models.load(self.clip.text_encoder)
-
-        # Load T5.
+    def _t5_encode(self, context: InvocationContext) -> torch.Tensor:
         t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer)
         t5_text_encoder_info = context.models.load(self.t5_encoder.text_encoder)
 
@@ -70,6 +68,15 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             prompt_embeds = t5_encoder(prompt)
 
+        assert isinstance(prompt_embeds, torch.Tensor)
+        return prompt_embeds
+
+    def _clip_encode(self, context: InvocationContext) -> torch.Tensor:
+        clip_tokenizer_info = context.models.load(self.clip.tokenizer)
+        clip_text_encoder_info = context.models.load(self.clip.text_encoder)
+
+        prompt = [self.prompt]
+
         with (
             clip_text_encoder_info as clip_text_encoder,
             clip_tokenizer_info as clip_tokenizer,
@@ -81,6 +88,5 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             pooled_prompt_embeds = clip_encoder(prompt)
 
-        assert isinstance(prompt_embeds, torch.Tensor)
         assert isinstance(pooled_prompt_embeds, torch.Tensor)
-        return prompt_embeds, pooled_prompt_embeds
+        return pooled_prompt_embeds

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/app/invocations/flux_text_to_image.py

@@ -58,13 +58,7 @@ class FluxTextToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the conditioning data.
-        cond_data = context.conditioning.load(self.positive_text_conditioning.conditioning_name)
-        assert len(cond_data.conditionings) == 1
-        flux_conditioning = cond_data.conditionings[0]
-        assert isinstance(flux_conditioning, FLUXConditioningInfo)
-
-        latents = self._run_diffusion(context, flux_conditioning.clip_embeds, flux_conditioning.t5_embeds)
+        latents = self._run_diffusion(context)
         image = self._run_vae_decoding(context, latents)
         image_dto = context.images.save(image=image)
         return ImageOutput.build(image_dto)
@@ -72,12 +66,20 @@ class FluxTextToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     def _run_diffusion(
         self,
         context: InvocationContext,
-        clip_embeddings: torch.Tensor,
-        t5_embeddings: torch.Tensor,
     ):
-        transformer_info = context.models.load(self.transformer.transformer)
         inference_dtype = torch.bfloat16
 
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(self.positive_text_conditioning.conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        flux_conditioning = cond_data.conditionings[0]
+        assert isinstance(flux_conditioning, FLUXConditioningInfo)
+        flux_conditioning = flux_conditioning.to(dtype=inference_dtype)
+        t5_embeddings = flux_conditioning.t5_embeds
+        clip_embeddings = flux_conditioning.clip_embeds
+
+        transformer_info = context.models.load(self.transformer.transformer)
+
         # Prepare input noise.
         x = get_noise(
             num_samples=1,
@@ -88,24 +90,19 @@ class FluxTextToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
             seed=self.seed,
         )
 
-        img, img_ids = prepare_latent_img_patches(x)
+        x, img_ids = prepare_latent_img_patches(x)
 
         is_schnell = "schnell" in transformer_info.config.config_path
 
         timesteps = get_schedule(
             num_steps=self.num_steps,
-            image_seq_len=img.shape[1],
+            image_seq_len=x.shape[1],
             shift=not is_schnell,
         )
 
         bs, t5_seq_len, _ = t5_embeddings.shape
         txt_ids = torch.zeros(bs, t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device())
 
-        # HACK(ryand): Manually empty the cache. Currently we don't check the size of the model before loading it from
-        # disk. Since the transformer model is large (24GB), there's a good chance that it will OOM on 32GB RAM systems
-        # if the cache is not empty.
-        context.models._services.model_manager.load.ram_cache.make_room(24 * 2**30)
-
         with transformer_info as transformer:
             assert isinstance(transformer, Flux)
 
@@ -140,7 +137,7 @@ class FluxTextToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
 
             x = denoise(
                 model=transformer,
-                img=img,
+                img=x,
                 img_ids=img_ids,
                 txt=t5_embeddings,
                 txt_ids=txt_ids,

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/app/invocations/model.py

@@ -157,7 +157,7 @@ class FluxModelLoaderOutput(BaseInvocationOutput):
     title="Flux Main Model",
     tags=["model", "flux"],
     category="model",
-    version="1.0.3",
+    version="1.0.4",
     classification=Classification.Prototype,
 )
 class FluxModelLoaderInvocation(BaseInvocation):
@@ -169,23 +169,35 @@ class FluxModelLoaderInvocation(BaseInvocation):
         input=Input.Direct,
     )
 
-    t5_encoder: ModelIdentifierField = InputField(
-        description=FieldDescriptions.t5_encoder,
-        ui_type=UIType.T5EncoderModel,
+    t5_encoder_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.t5_encoder, ui_type=UIType.T5EncoderModel, input=Input.Direct, title="T5 Encoder"
+    )
+
+    clip_embed_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.clip_embed_model,
+        ui_type=UIType.CLIPEmbedModel,
         input=Input.Direct,
+        title="CLIP Embed",
+    )
+
+    vae_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.vae_model, ui_type=UIType.FluxVAEModel, title="VAE"
     )
 
     def invoke(self, context: InvocationContext) -> FluxModelLoaderOutput:
-        model_key = self.model.key
-
-        if not context.models.exists(model_key):
-            raise ValueError(f"Unknown model: {model_key}")
-        transformer = self._get_model(context, SubModelType.Transformer)
-        tokenizer = self._get_model(context, SubModelType.Tokenizer)
-        tokenizer2 = self._get_model(context, SubModelType.Tokenizer2)
-        clip_encoder = self._get_model(context, SubModelType.TextEncoder)
-        t5_encoder = self._get_model(context, SubModelType.TextEncoder2)
-        vae = self._get_model(context, SubModelType.VAE)
+        for key in [self.model.key, self.t5_encoder_model.key, self.clip_embed_model.key, self.vae_model.key]:
+            if not context.models.exists(key):
+                raise ValueError(f"Unknown model: {key}")
+
+        transformer = self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
+        vae = self.vae_model.model_copy(update={"submodel_type": SubModelType.VAE})
+
+        tokenizer = self.clip_embed_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
+        clip_encoder = self.clip_embed_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
+
+        tokenizer2 = self.t5_encoder_model.model_copy(update={"submodel_type": SubModelType.Tokenizer2})
+        t5_encoder = self.t5_encoder_model.model_copy(update={"submodel_type": SubModelType.TextEncoder2})
+
         transformer_config = context.models.get_config(transformer)
         assert isinstance(transformer_config, CheckpointConfigBase)
 
@@ -197,52 +209,6 @@ class FluxModelLoaderInvocation(BaseInvocation):
             max_seq_len=max_seq_lengths[transformer_config.config_path],
         )
 
-    def _get_model(self, context: InvocationContext, submodel: SubModelType) -> ModelIdentifierField:
-        match submodel:
-            case SubModelType.Transformer:
-                return self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
-            case SubModelType.VAE:
-                return self._pull_model_from_mm(
-                    context,
-                    SubModelType.VAE,
-                    "FLUX.1-schnell_ae",
-                    ModelType.VAE,
-                    BaseModelType.Flux,
-                )
-            case submodel if submodel in [SubModelType.Tokenizer, SubModelType.TextEncoder]:
-                return self._pull_model_from_mm(
-                    context,
-                    submodel,
-                    "clip-vit-large-patch14",
-                    ModelType.CLIPEmbed,
-                    BaseModelType.Any,
-                )
-            case submodel if submodel in [SubModelType.Tokenizer2, SubModelType.TextEncoder2]:
-                return self._pull_model_from_mm(
-                    context,
-                    submodel,
-                    self.t5_encoder.name,
-                    ModelType.T5Encoder,
-                    BaseModelType.Any,
-                )
-            case _:
-                raise Exception(f"{submodel.value} is not a supported submodule for a flux model")
-
-    def _pull_model_from_mm(
-        self,
-        context: InvocationContext,
-        submodel: SubModelType,
-        name: str,
-        type: ModelType,
-        base: BaseModelType,
-    ):
-        if models := context.models.search_by_attrs(name=name, base=base, type=type):
-            if len(models) != 1:
-                raise Exception(f"Multiple models detected for selected model with name {name}")
-            return ModelIdentifierField.from_config(models[0]).model_copy(update={"submodel_type": submodel})
-        else:
-            raise ValueError(f"Please install the {base}:{type} model named {name} via starter models")
-
 
 @invocation(
     "main_model_loader",

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/app/services/workflow_records/default_workflows/Flux Text to Image.json

@@ -2,13 +2,13 @@
   "name": "FLUX Text to Image",
   "author": "InvokeAI",
   "description": "A simple text-to-image workflow using FLUX dev or schnell models. Prerequisite model downloads: T5 Encoder, CLIP-L Encoder, and FLUX VAE. Quantized and un-quantized versions can be found in the starter models tab within your Model Manager. We recommend 4 steps for FLUX schnell models and 30 steps for FLUX dev models.",
-  "version": "1.0.0",
+  "version": "1.0.4",
   "contact": "",
   "tags": "text2image, flux",
   "notes": "Prerequisite model downloads: T5 Encoder, CLIP-L Encoder, and FLUX VAE. Quantized and un-quantized versions can be found in the starter models tab within your Model Manager. We recommend 4 steps for FLUX schnell models and 30 steps for FLUX dev models.",
   "exposedFields": [
     {
-      "nodeId": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+      "nodeId": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
       "fieldName": "model"
     },
     {
@@ -20,8 +20,8 @@
       "fieldName": "num_steps"
     },
     {
-      "nodeId": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
-      "fieldName": "t5_encoder"
+      "nodeId": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
+      "fieldName": "t5_encoder_model"
     }
   ],
   "meta": {
@@ -30,12 +30,12 @@
   },
   "nodes": [
     {
-      "id": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+      "id": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
       "type": "invocation",
       "data": {
-        "id": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+        "id": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
         "type": "flux_model_loader",
-        "version": "1.0.3",
+        "version": "1.0.4",
         "label": "",
         "notes": "",
         "isOpen": true,
@@ -44,31 +44,25 @@
         "inputs": {
           "model": {
             "name": "model",
-            "label": "Model (Starter Models can be found in Model Manager)",
-            "value": {
-              "key": "f04a7a2f-c74d-4538-8d5e-879a53501662",
-              "hash": "random:4875da7a9508444ffa706f61961c260d0c6729f6181a86b31fad06df1277b850",
-              "name": "FLUX Dev (Quantized)",
-              "base": "flux",
-              "type": "main"
-            }
+            "label": ""
           },
-          "t5_encoder": {
-            "name": "t5_encoder",
-            "label": "T 5 Encoder (Starter Models can be found in Model Manager)",
-            "value": {
-              "key": "20dcd9ec-5fbb-4012-8401-049e707da5e5",
-              "hash": "random:f986be43ff3502169e4adbdcee158afb0e0a65a1edc4cab16ae59963630cfd8f",
-              "name": "t5_bnb_int8_quantized_encoder",
-              "base": "any",
-              "type": "t5_encoder"
-            }
+          "t5_encoder_model": {
+            "name": "t5_encoder_model",
+            "label": ""
+          },
+          "clip_embed_model": {
+            "name": "clip_embed_model",
+            "label": ""
+          },
+          "vae_model": {
+            "name": "vae_model",
+            "label": ""
           }
         }
       },
       "position": {
-        "x": 337.09365228062825,
-        "y": 40.63469521079861
+        "x": 381.1882713063478,
+        "y": -95.89663532854017
       }
     },
     {
@@ -207,45 +201,45 @@
   ],
   "edges": [
     {
-      "id": "reactflow__edge-4f0207c2-ff40-41fd-b047-ad33fbb1c33amax_seq_len-01f674f8-b3d1-4df1-acac-6cb8e0bfb63ct5_max_seq_len",
+      "id": "reactflow__edge-f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90max_seq_len-01f674f8-b3d1-4df1-acac-6cb8e0bfb63ct5_max_seq_len",
       "type": "default",
-      "source": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+      "source": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
       "target": "01f674f8-b3d1-4df1-acac-6cb8e0bfb63c",
       "sourceHandle": "max_seq_len",
       "targetHandle": "t5_max_seq_len"
     },
     {
-      "id": "reactflow__edge-4f0207c2-ff40-41fd-b047-ad33fbb1c33avae-159bdf1b-79e7-4174-b86e-d40e646964c8vae",
+      "id": "reactflow__edge-f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90vae-159bdf1b-79e7-4174-b86e-d40e646964c8vae",
       "type": "default",
-      "source": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+      "source": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
       "target": "159bdf1b-79e7-4174-b86e-d40e646964c8",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     },
     {
-      "id": "reactflow__edge-4f0207c2-ff40-41fd-b047-ad33fbb1c33atransformer-159bdf1b-79e7-4174-b86e-d40e646964c8transformer",
-      "type": "default",
-      "source": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
-      "target": "159bdf1b-79e7-4174-b86e-d40e646964c8",
-      "sourceHandle": "transformer",
-      "targetHandle": "transformer"
-    },
-    {
-      "id": "reactflow__edge-4f0207c2-ff40-41fd-b047-ad33fbb1c33at5_encoder-01f674f8-b3d1-4df1-acac-6cb8e0bfb63ct5_encoder",
+      "id": "reactflow__edge-f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90t5_encoder-01f674f8-b3d1-4df1-acac-6cb8e0bfb63ct5_encoder",
       "type": "default",
-      "source": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+      "source": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
       "target": "01f674f8-b3d1-4df1-acac-6cb8e0bfb63c",
       "sourceHandle": "t5_encoder",
       "targetHandle": "t5_encoder"
     },
     {
-      "id": "reactflow__edge-4f0207c2-ff40-41fd-b047-ad33fbb1c33aclip-01f674f8-b3d1-4df1-acac-6cb8e0bfb63cclip",
+      "id": "reactflow__edge-f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90clip-01f674f8-b3d1-4df1-acac-6cb8e0bfb63cclip",
       "type": "default",
-      "source": "4f0207c2-ff40-41fd-b047-ad33fbb1c33a",
+      "source": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
       "target": "01f674f8-b3d1-4df1-acac-6cb8e0bfb63c",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
+    {
+      "id": "reactflow__edge-f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90transformer-159bdf1b-79e7-4174-b86e-d40e646964c8transformer",
+      "type": "default",
+      "source": "f8d9d7c8-9ed7-4bd7-9e42-ab0e89bfac90",
+      "target": "159bdf1b-79e7-4174-b86e-d40e646964c8",
+      "sourceHandle": "transformer",
+      "targetHandle": "transformer"
+    },
     {
       "id": "reactflow__edge-01f674f8-b3d1-4df1-acac-6cb8e0bfb63cconditioning-159bdf1b-79e7-4174-b86e-d40e646964c8positive_text_conditioning",
       "type": "default",

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/backend/flux/sampling.py

@@ -111,16 +111,7 @@ def denoise(
     step_callback: Callable[[], None],
     guidance: float = 4.0,
 ):
-    dtype = model.txt_in.bias.dtype
-
-    # TODO(ryand): This shouldn't be necessary if we manage the dtypes properly in the caller.
-    img = img.to(dtype=dtype)
-    img_ids = img_ids.to(dtype=dtype)
-    txt = txt.to(dtype=dtype)
-    txt_ids = txt_ids.to(dtype=dtype)
-    vec = vec.to(dtype=dtype)
-
-    # this is ignored for schnell
+    # guidance_vec is ignored for schnell.
     guidance_vec = torch.full((img.shape[0],), guidance, device=img.device, dtype=img.dtype)
     for t_curr, t_prev in tqdm(list(zip(timesteps[:-1], timesteps[1:], strict=True))):
         t_vec = torch.full((img.shape[0],), t_curr, dtype=img.dtype, device=img.device)
@@ -168,9 +159,9 @@ def prepare_latent_img_patches(latent_img: torch.Tensor) -> tuple[torch.Tensor,
         img = repeat(img, "1 ... -> bs ...", bs=bs)
 
     # Generate patch position ids.
-    img_ids = torch.zeros(h // 2, w // 2, 3, device=img.device)
-    img_ids[..., 1] = img_ids[..., 1] + torch.arange(h // 2, device=img.device)[:, None]
-    img_ids[..., 2] = img_ids[..., 2] + torch.arange(w // 2, device=img.device)[None, :]
+    img_ids = torch.zeros(h // 2, w // 2, 3, device=img.device, dtype=img.dtype)
+    img_ids[..., 1] = img_ids[..., 1] + torch.arange(h // 2, device=img.device, dtype=img.dtype)[:, None]
+    img_ids[..., 2] = img_ids[..., 2] + torch.arange(w // 2, device=img.device, dtype=img.dtype)[None, :]
     img_ids = repeat(img_ids, "h w c -> b (h w) c", b=bs)
 
     return img, img_ids

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/backend/model_manager/load/load_default.py

@@ -72,6 +72,7 @@ class ModelLoader(ModelLoaderBase):
             pass
 
         config.path = str(self._get_model_path(config))
+        self._ram_cache.make_room(self.get_size_fs(config, Path(config.path), submodel_type))
         loaded_model = self._load_model(config, submodel_type)
 
         self._ram_cache.put(

{InvokeAI-4.2.9.dev8 → InvokeAI-4.2.9.dev10}/invokeai/backend/model_manager/load/model_cache/model_cache_base.py

@@ -193,15 +193,6 @@ class ModelCacheBase(ABC, Generic[T]):
         """
         pass
 
-    @abstractmethod
-    def exists(
-        self,
-        key: str,
-        submodel_type: Optional[SubModelType] = None,
-    ) -> bool:
-        """Return true if the model identified by key and submodel_type is in the cache."""
-        pass
-
     @abstractmethod
     def cache_size(self) -> int:
         """Get the total size of the models currently cached."""