InvokeAI 5.4.0__tar.gz → 5.4.1__tar.gz

{invokeai-5.4.0 → invokeai-5.4.1}/InvokeAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 5.4.0
+Version: 5.4.1
 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-5.4.0 → invokeai-5.4.1}/InvokeAI.egg-info/SOURCES.txt

@@ -78,6 +78,7 @@ invokeai/app/invocations/prompt.py
 invokeai/app/invocations/resize_latents.py
 invokeai/app/invocations/scheduler.py
 invokeai/app/invocations/sd3_denoise.py
+invokeai/app/invocations/sd3_image_to_latents.py
 invokeai/app/invocations/sd3_latents_to_image.py
 invokeai/app/invocations/sd3_model_loader.py
 invokeai/app/invocations/sd3_text_encoder.py
@@ -451,6 +452,9 @@ invokeai/backend/quantization/gguf/utils.py
 invokeai/backend/quantization/scripts/load_flux_model_bnb_llm_int8.py
 invokeai/backend/quantization/scripts/load_flux_model_bnb_nf4.py
 invokeai/backend/quantization/scripts/quantize_t5_xxl_bnb_llm_int8.py
+invokeai/backend/sd3/__init__.py
+invokeai/backend/sd3/extensions/__init__.py
+invokeai/backend/sd3/extensions/inpaint_extension.py
 invokeai/backend/stable_diffusion/__init__.py
 invokeai/backend/stable_diffusion/denoise_context.py
 invokeai/backend/stable_diffusion/diffusers_pipeline.py
@@ -519,12 +523,13 @@ 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-Cgdz1lBg.js
+invokeai/frontend/web/dist/assets/App-B0FpUdCl.js
 invokeai/frontend/web/dist/assets/App-DEu4J2pT.css
 invokeai/frontend/web/dist/assets/ThemeLocaleProvider-B2NxUfIp.css
-invokeai/frontend/web/dist/assets/ThemeLocaleProvider-QXscVpCV.js
+invokeai/frontend/web/dist/assets/ThemeLocaleProvider-_06ioAWc.js
 invokeai/frontend/web/dist/assets/commercial-license-bg-C_dHp7on.png
-invokeai/frontend/web/dist/assets/index-DT5PJ9-6.js
+invokeai/frontend/web/dist/assets/denoising-strength-4mznP2tj.png
+invokeai/frontend/web/dist/assets/index-DOkD_T-j.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
@@ -532,8 +537,10 @@ invokeai/frontend/web/dist/assets/inter-greek-wght-normal-CaVNZxsx.woff2
 invokeai/frontend/web/dist/assets/inter-latin-ext-wght-normal-CFHvXkgd.woff2
 invokeai/frontend/web/dist/assets/inter-latin-wght-normal-C2S99t-D.woff2
 invokeai/frontend/web/dist/assets/inter-vietnamese-wght-normal-CBcvBZtf.woff2
+invokeai/frontend/web/dist/assets/useTranslation-ijkhTtpL.js
 invokeai/frontend/web/dist/assets/worker-Dywf1EVc.js
 invokeai/frontend/web/dist/assets/images/commercial-license-bg.png
+invokeai/frontend/web/dist/assets/images/denoising-strength.png
 invokeai/frontend/web/dist/assets/images/invoke-alert-favicon.svg
 invokeai/frontend/web/dist/assets/images/invoke-avatar-circle.svg
 invokeai/frontend/web/dist/assets/images/invoke-avatar-square.svg

{invokeai-5.4.0 → invokeai-5.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 5.4.0
+Version: 5.4.1
 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-5.4.0 → invokeai-5.4.1}/invokeai/app/api/routers/app_info.py

@@ -40,6 +40,8 @@ class AppVersion(BaseModel):
 
     version: str = Field(description="App version")
 
+    highlights: Optional[list[str]] = Field(default=None, description="Highlights of release")
+
 
 class AppDependencyVersions(BaseModel):
     """App depencency Versions Response"""

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/compel.py

@@ -95,6 +95,7 @@ class CompelInvocation(BaseInvocation):
                 ti_manager,
             ),
         ):
+            context.util.signal_progress("Building conditioning")
             assert isinstance(text_encoder, CLIPTextModel)
             assert isinstance(tokenizer, CLIPTokenizer)
             compel = Compel(
@@ -191,6 +192,7 @@ class SDXLPromptInvocationBase:
                 ti_manager,
             ),
         ):
+            context.util.signal_progress("Building conditioning")
             assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
             assert isinstance(tokenizer, CLIPTokenizer)
 

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/create_denoise_mask.py

@@ -65,6 +65,7 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
             img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
             masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
+            context.util.signal_progress("Running VAE encoder")
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
             masked_latents_name = context.tensors.save(tensor=masked_latents)

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/create_gradient_mask.py

@@ -131,6 +131,7 @@ class CreateGradientMaskInvocation(BaseInvocation):
                     image_tensor = image_tensor.unsqueeze(0)
                 img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
                 masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
+                context.util.signal_progress("Running VAE encoder")
                 masked_latents = ImageToLatentsInvocation.vae_encode(
                     vae_info, self.fp32, self.tiled, masked_image.clone()
                 )

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/flux_denoise.py

@@ -56,7 +56,7 @@ from invokeai.backend.util.devices import TorchDevice
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="3.2.0",
+    version="3.2.1",
     classification=Classification.Prototype,
 )
 class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -81,6 +81,7 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
+    add_noise: bool = InputField(default=True, description="Add noise based on denoising start.")
     transformer: TransformerField = InputField(
         description=FieldDescriptions.flux_model,
         input=Input.Connection,
@@ -207,9 +208,12 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                     "to be poor. Consider using a FLUX dev model instead."
                 )
 
-            # Noise the orig_latents by the appropriate amount for the first timestep.
-            t_0 = timesteps[0]
-            x = t_0 * noise + (1.0 - t_0) * init_latents
+            if self.add_noise:
+                # Noise the orig_latents by the appropriate amount for the first timestep.
+                t_0 = timesteps[0]
+                x = t_0 * noise + (1.0 - t_0) * init_latents
+            else:
+                x = init_latents
         else:
             # init_latents are not provided, so we are not doing image-to-image (i.e. we are starting from pure noise).
             if self.denoising_start > 1e-5:

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/flux_text_encoder.py

@@ -71,6 +71,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             t5_encoder = HFEncoder(t5_text_encoder, t5_tokenizer, False, self.t5_max_seq_len)
 
+            context.util.signal_progress("Running T5 encoder")
             prompt_embeds = t5_encoder(prompt)
 
         assert isinstance(prompt_embeds, torch.Tensor)
@@ -111,6 +112,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             clip_encoder = HFEncoder(clip_text_encoder, clip_tokenizer, True, 77)
 
+            context.util.signal_progress("Running CLIP encoder")
             pooled_prompt_embeds = clip_encoder(prompt)
 
         assert isinstance(pooled_prompt_embeds, torch.Tensor)

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/flux_vae_decode.py

@@ -41,7 +41,8 @@ class FluxVaeDecodeInvocation(BaseInvocation, WithMetadata, WithBoard):
     def _vae_decode(self, vae_info: LoadedModel, latents: torch.Tensor) -> Image.Image:
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype())
+            vae_dtype = next(iter(vae.parameters())).dtype
+            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
             img = vae.decode(latents)
 
         img = img.clamp(-1, 1)
@@ -53,6 +54,7 @@ class FluxVaeDecodeInvocation(BaseInvocation, WithMetadata, WithBoard):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.tensors.load(self.latents.latents_name)
         vae_info = context.models.load(self.vae.vae)
+        context.util.signal_progress("Running VAE")
         image = self._vae_decode(vae_info=vae_info, latents=latents)
 
         TorchDevice.empty_cache()

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/flux_vae_encode.py

@@ -44,9 +44,8 @@ class FluxVaeEncodeInvocation(BaseInvocation):
         generator = torch.Generator(device=TorchDevice.choose_torch_device()).manual_seed(0)
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            image_tensor = image_tensor.to(
-                device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype()
-            )
+            vae_dtype = next(iter(vae.parameters())).dtype
+            image_tensor = image_tensor.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
             latents = vae.encode(image_tensor, sample=True, generator=generator)
             return latents
 
@@ -60,6 +59,7 @@ class FluxVaeEncodeInvocation(BaseInvocation):
         if image_tensor.dim() == 3:
             image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
 
+        context.util.signal_progress("Running VAE")
         latents = self.vae_encode(vae_info=vae_info, image_tensor=image_tensor)
 
         latents = latents.to("cpu")

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/image_to_latents.py

@@ -117,6 +117,7 @@ class ImageToLatentsInvocation(BaseInvocation):
         if image_tensor.dim() == 3:
             image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
 
+        context.util.signal_progress("Running VAE encoder")
         latents = self.vae_encode(
             vae_info=vae_info, upcast=self.fp32, tiled=self.tiled, image_tensor=image_tensor, tile_size=self.tile_size
         )

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/latents_to_image.py

@@ -60,6 +60,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         vae_info = context.models.load(self.vae.vae)
         assert isinstance(vae_info.model, (AutoencoderKL, AutoencoderTiny))
         with SeamlessExt.static_patch_model(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            context.util.signal_progress("Running VAE decoder")
             assert isinstance(vae, (AutoencoderKL, AutoencoderTiny))
             latents = latents.to(vae.device)
             if self.fp32:

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/metadata.py

@@ -147,6 +147,10 @@ GENERATION_MODES = Literal[
     "flux_img2img",
     "flux_inpaint",
     "flux_outpaint",
+    "sd3_txt2img",
+    "sd3_img2img",
+    "sd3_inpaint",
+    "sd3_outpaint",
 ]
 
 

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/sd3_denoise.py

@@ -1,16 +1,19 @@
-from typing import Callable, Tuple
+from typing import Callable, Optional, Tuple
 
 import torch
+import torchvision.transforms as tv_transforms
 from diffusers.models.transformers.transformer_sd3 import SD3Transformer2DModel
-from diffusers.schedulers.scheduling_flow_match_euler_discrete import FlowMatchEulerDiscreteScheduler
+from torchvision.transforms.functional import resize as tv_resize
 from tqdm import tqdm
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
 from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
 from invokeai.app.invocations.fields import (
+    DenoiseMaskField,
     FieldDescriptions,
     Input,
     InputField,
+    LatentsField,
     SD3ConditioningField,
     WithBoard,
     WithMetadata,
@@ -19,7 +22,9 @@ from invokeai.app.invocations.model import TransformerField
 from invokeai.app.invocations.primitives import LatentsOutput
 from invokeai.app.invocations.sd3_text_encoder import SD3_T5_MAX_SEQ_LEN
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.flux.sampling_utils import clip_timestep_schedule_fractional
 from invokeai.backend.model_manager.config import BaseModelType
+from invokeai.backend.sd3.extensions.inpaint_extension import InpaintExtension
 from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import SD3ConditioningInfo
 from invokeai.backend.util.devices import TorchDevice
@@ -30,16 +35,24 @@ from invokeai.backend.util.devices import TorchDevice
     title="SD3 Denoise",
     tags=["image", "sd3"],
     category="image",
-    version="1.0.0",
+    version="1.1.0",
     classification=Classification.Prototype,
 )
 class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Run denoising process with a SD3 model."""
 
+    # If latents is provided, this means we are doing image-to-image.
+    latents: Optional[LatentsField] = InputField(
+        default=None, description=FieldDescriptions.latents, input=Input.Connection
+    )
+    # denoise_mask is used for image-to-image inpainting. Only the masked region is modified.
+    denoise_mask: Optional[DenoiseMaskField] = InputField(
+        default=None, description=FieldDescriptions.denoise_mask, input=Input.Connection
+    )
+    denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
+    denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
     transformer: TransformerField = InputField(
-        description=FieldDescriptions.sd3_model,
-        input=Input.Connection,
-        title="Transformer",
+        description=FieldDescriptions.sd3_model, input=Input.Connection, title="Transformer"
     )
     positive_conditioning: SD3ConditioningField = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection
@@ -61,6 +74,41 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         name = context.tensors.save(tensor=latents)
         return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
+    def _prep_inpaint_mask(self, context: InvocationContext, latents: torch.Tensor) -> torch.Tensor | None:
+        """Prepare the inpaint mask.
+        - Loads the mask
+        - Resizes if necessary
+        - Casts to same device/dtype as latents
+
+        Args:
+            context (InvocationContext): The invocation context, for loading the inpaint mask.
+            latents (torch.Tensor): A latent image tensor. Used to determine the target shape, device, and dtype for the
+                inpaint mask.
+
+        Returns:
+            torch.Tensor | None: Inpaint mask. Values of 0.0 represent the regions to be fully denoised, and 1.0
+                represent the regions to be preserved.
+        """
+        if self.denoise_mask is None:
+            return None
+        mask = context.tensors.load(self.denoise_mask.mask_name)
+
+        # The input denoise_mask contains values in [0, 1], where 0.0 represents the regions to be fully denoised, and
+        # 1.0 represents the regions to be preserved.
+        # We invert the mask so that the regions to be preserved are 0.0 and the regions to be denoised are 1.0.
+        mask = 1.0 - mask
+
+        _, _, latent_height, latent_width = latents.shape
+        mask = tv_resize(
+            img=mask,
+            size=[latent_height, latent_width],
+            interpolation=tv_transforms.InterpolationMode.BILINEAR,
+            antialias=False,
+        )
+
+        mask = mask.to(device=latents.device, dtype=latents.dtype)
+        return mask
+
     def _load_text_conditioning(
         self,
         context: InvocationContext,
@@ -170,14 +218,20 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         prompt_embeds = torch.cat([neg_prompt_embeds, pos_prompt_embeds], dim=0)
         pooled_prompt_embeds = torch.cat([neg_pooled_prompt_embeds, pos_pooled_prompt_embeds], dim=0)
 
-        # Prepare the scheduler.
-        scheduler = FlowMatchEulerDiscreteScheduler()
-        scheduler.set_timesteps(num_inference_steps=self.steps, device=device)
-        timesteps = scheduler.timesteps
-        assert isinstance(timesteps, torch.Tensor)
+        # Prepare the timestep schedule.
+        # We add an extra step to the end to account for the final timestep of 0.0.
+        timesteps: list[float] = torch.linspace(1, 0, self.steps + 1).tolist()
+        # Clip the timesteps schedule based on denoising_start and denoising_end.
+        timesteps = clip_timestep_schedule_fractional(timesteps, self.denoising_start, self.denoising_end)
+        total_steps = len(timesteps) - 1
 
         # Prepare the CFG scale list.
-        cfg_scale = self._prepare_cfg_scale(len(timesteps))
+        cfg_scale = self._prepare_cfg_scale(total_steps)
+
+        # Load the input latents, if provided.
+        init_latents = context.tensors.load(self.latents.latents_name) if self.latents else None
+        if init_latents is not None:
+            init_latents = init_latents.to(device=device, dtype=inference_dtype)
 
         # Generate initial latent noise.
         num_channels_latents = transformer_info.model.config.in_channels
@@ -191,9 +245,34 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             device=device,
             seed=self.seed,
         )
-        latents: torch.Tensor = noise
 
-        total_steps = len(timesteps)
+        # Prepare input latent image.
+        if init_latents is not None:
+            # Noise the init_latents by the appropriate amount for the first timestep.
+            t_0 = timesteps[0]
+            latents = t_0 * noise + (1.0 - t_0) * init_latents
+        else:
+            # init_latents are not provided, so we are not doing image-to-image (i.e. we are starting from pure noise).
+            if self.denoising_start > 1e-5:
+                raise ValueError("denoising_start should be 0 when initial latents are not provided.")
+            latents = noise
+
+        # If len(timesteps) == 1, then short-circuit. We are just noising the input latents, but not taking any
+        # denoising steps.
+        if len(timesteps) <= 1:
+            return latents
+
+        # Prepare inpaint extension.
+        inpaint_mask = self._prep_inpaint_mask(context, latents)
+        inpaint_extension: InpaintExtension | None = None
+        if inpaint_mask is not None:
+            assert init_latents is not None
+            inpaint_extension = InpaintExtension(
+                init_latents=init_latents,
+                inpaint_mask=inpaint_mask,
+                noise=noise,
+            )
+
         step_callback = self._build_step_callback(context)
 
         step_callback(
@@ -210,11 +289,12 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             assert isinstance(transformer, SD3Transformer2DModel)
 
             # 6. Denoising loop
-            for step_idx, t in tqdm(list(enumerate(timesteps))):
+            for step_idx, (t_curr, t_prev) in tqdm(list(enumerate(zip(timesteps[:-1], timesteps[1:], strict=True)))):
                 # Expand the latents if we are doing CFG.
                 latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
                 # Expand the timestep to match the latent model input.
-                timestep = t.expand(latent_model_input.shape[0])
+                # Multiply by 1000 to match the default FlowMatchEulerDiscreteScheduler num_train_timesteps.
+                timestep = torch.tensor([t_curr * 1000], device=device).expand(latent_model_input.shape[0])
 
                 noise_pred = transformer(
                     hidden_states=latent_model_input,
@@ -232,21 +312,19 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
                 # Compute the previous noisy sample x_t -> x_t-1.
                 latents_dtype = latents.dtype
-                latents = scheduler.step(model_output=noise_pred, timestep=t, sample=latents, return_dict=False)[0]
+                latents = latents.to(dtype=torch.float32)
+                latents = latents + (t_prev - t_curr) * noise_pred
+                latents = latents.to(dtype=latents_dtype)
 
-                # TODO(ryand): This MPS dtype handling was copied from diffusers, I haven't tested to see if it's
-                # needed.
-                if latents.dtype != latents_dtype:
-                    if torch.backends.mps.is_available():
-                        # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
-                        latents = latents.to(latents_dtype)
+                if inpaint_extension is not None:
+                    latents = inpaint_extension.merge_intermediate_latents_with_init_latents(latents, t_prev)
 
                 step_callback(
                     PipelineIntermediateState(
                         step=step_idx + 1,
                         order=1,
                         total_steps=total_steps,
-                        timestep=int(t),
+                        timestep=int(t_curr),
                         latents=latents,
                     ),
                 )

invokeai-5.4.1/invokeai/app/invocations/sd3_image_to_latents.py

@@ -0,0 +1,65 @@
+import einops
+import torch
+from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import VAEField
+from invokeai.app.invocations.primitives import LatentsOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.load.load_base import LoadedModel
+from invokeai.backend.stable_diffusion.diffusers_pipeline import image_resized_to_grid_as_tensor
+
+
+@invocation(
+    "sd3_i2l",
+    title="SD3 Image to Latents",
+    tags=["image", "latents", "vae", "i2l", "sd3"],
+    category="image",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class SD3ImageToLatentsInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Generates latents from an image."""
+
+    image: ImageField = InputField(description="The image to encode")
+    vae: VAEField = InputField(description=FieldDescriptions.vae, input=Input.Connection)
+
+    @staticmethod
+    def vae_encode(vae_info: LoadedModel, image_tensor: torch.Tensor) -> torch.Tensor:
+        with vae_info as vae:
+            assert isinstance(vae, AutoencoderKL)
+
+            vae.disable_tiling()
+
+            image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
+            with torch.inference_mode():
+                image_tensor_dist = vae.encode(image_tensor).latent_dist
+                # TODO: Use seed to make sampling reproducible.
+                latents: torch.Tensor = image_tensor_dist.sample().to(dtype=vae.dtype)
+
+            latents = vae.config.scaling_factor * latents
+
+        return latents
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        image = context.images.get_pil(self.image.image_name)
+
+        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+        if image_tensor.dim() == 3:
+            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
+
+        vae_info = context.models.load(self.vae.vae)
+        latents = self.vae_encode(vae_info=vae_info, image_tensor=image_tensor)
+
+        latents = latents.to("cpu")
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/sd3_latents_to_image.py

@@ -47,6 +47,7 @@ class SD3LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         vae_info = context.models.load(self.vae.vae)
         assert isinstance(vae_info.model, (AutoencoderKL))
         with SeamlessExt.static_patch_model(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            context.util.signal_progress("Running VAE")
             assert isinstance(vae, (AutoencoderKL))
             latents = latents.to(vae.device)
 

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/invocations/sd3_text_encoder.py

@@ -95,6 +95,7 @@ class Sd3TextEncoderInvocation(BaseInvocation):
             t5_text_encoder_info as t5_text_encoder,
             t5_tokenizer_info as t5_tokenizer,
         ):
+            context.util.signal_progress("Running T5 encoder")
             assert isinstance(t5_text_encoder, T5EncoderModel)
             assert isinstance(t5_tokenizer, (T5Tokenizer, T5TokenizerFast))
 
@@ -137,6 +138,7 @@ class Sd3TextEncoderInvocation(BaseInvocation):
             clip_tokenizer_info as clip_tokenizer,
             ExitStack() as exit_stack,
         ):
+            context.util.signal_progress("Running CLIP encoder")
             assert isinstance(clip_text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
             assert isinstance(clip_tokenizer, CLIPTokenizer)
 

{invokeai-5.4.0 → invokeai-5.4.1}/invokeai/app/services/shared/invocation_context.py

@@ -160,6 +160,10 @@ class LoggerInterface(InvocationContextInterface):
 
 
 class ImagesInterface(InvocationContextInterface):
+    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
+        super().__init__(services, data)
+        self._util = util
+
     def save(
         self,
         image: Image,
@@ -186,6 +190,8 @@ class ImagesInterface(InvocationContextInterface):
             The saved image DTO.
         """
 
+        self._util.signal_progress("Saving image")
+
         # If `metadata` is provided directly, use that. Else, use the metadata provided by `WithMetadata`, falling back to None.
         metadata_ = None
         if metadata:
@@ -336,6 +342,10 @@ class ConditioningInterface(InvocationContextInterface):
 class ModelsInterface(InvocationContextInterface):
     """Common API for loading, downloading and managing models."""
 
+    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
+        super().__init__(services, data)
+        self._util = util
+
     def exists(self, identifier: Union[str, "ModelIdentifierField"]) -> bool:
         """Check if a model exists.
 
@@ -368,11 +378,15 @@ class ModelsInterface(InvocationContextInterface):
 
         if isinstance(identifier, str):
             model = self._services.model_manager.store.get_model(identifier)
-            return self._services.model_manager.load.load_model(model, submodel_type)
         else:
-            _submodel_type = submodel_type or identifier.submodel_type
+            submodel_type = submodel_type or identifier.submodel_type
             model = self._services.model_manager.store.get_model(identifier.key)
-            return self._services.model_manager.load.load_model(model, _submodel_type)
+
+        message = f"Loading model {model.name}"
+        if submodel_type:
+            message += f" ({submodel_type.value})"
+        self._util.signal_progress(message)
+        return self._services.model_manager.load.load_model(model, submodel_type)
 
     def load_by_attrs(
         self, name: str, base: BaseModelType, type: ModelType, submodel_type: Optional[SubModelType] = None
@@ -397,6 +411,10 @@ class ModelsInterface(InvocationContextInterface):
         if len(configs) > 1:
             raise ValueError(f"More than one model found with name {name}, base {base}, and type {type}")
 
+        message = f"Loading model {name}"
+        if submodel_type:
+            message += f" ({submodel_type.value})"
+        self._util.signal_progress(message)
         return self._services.model_manager.load.load_model(configs[0], submodel_type)
 
     def get_config(self, identifier: Union[str, "ModelIdentifierField"]) -> AnyModelConfig:
@@ -467,6 +485,7 @@ class ModelsInterface(InvocationContextInterface):
         Returns:
             Path to the downloaded model
         """
+        self._util.signal_progress(f"Downloading model {source}")
         return self._services.model_manager.install.download_and_cache_model(source=source)
 
     def load_local_model(
@@ -489,6 +508,8 @@ class ModelsInterface(InvocationContextInterface):
         Returns:
             A LoadedModelWithoutConfig object.
         """
+
+        self._util.signal_progress(f"Loading model {model_path.name}")
         return self._services.model_manager.load.load_model_from_path(model_path=model_path, loader=loader)
 
     def load_remote_model(
@@ -514,6 +535,8 @@ class ModelsInterface(InvocationContextInterface):
             A LoadedModelWithoutConfig object.
         """
         model_path = self._services.model_manager.install.download_and_cache_model(source=str(source))
+
+        self._util.signal_progress(f"Loading model {source}")
         return self._services.model_manager.load.load_model_from_path(model_path=model_path, loader=loader)
 
 
@@ -707,12 +730,12 @@ def build_invocation_context(
     """
 
     logger = LoggerInterface(services=services, data=data)
-    images = ImagesInterface(services=services, data=data)
     tensors = TensorsInterface(services=services, data=data)
-    models = ModelsInterface(services=services, data=data)
     config = ConfigInterface(services=services, data=data)
     util = UtilInterface(services=services, data=data, is_canceled=is_canceled)
     conditioning = ConditioningInterface(services=services, data=data)
+    models = ModelsInterface(services=services, data=data, util=util)
+    images = ImagesInterface(services=services, data=data, util=util)
     boards = BoardsInterface(services=services, data=data)
 
     ctx = InvocationContext(