Merge branch 'main' into lstein/chore/v6.10.0

Author: lstein

.github/CODEOWNERS

@@ -6,7 +6,7 @@
 /mkdocs.yml @lstein @blessedcoolant  
 
 # nodes
-/invokeai/app/ @blessedcoolant @lstein 
+/invokeai/app/ @blessedcoolant @lstein @dunkeroni @JPPhoto
 
 # installation and configuration
 /pyproject.toml  @lstein @blessedcoolant  
@@ -18,15 +18,15 @@
 /invokeai/version @lstein @blessedcoolant  
 
 # web ui
-/invokeai/frontend @blessedcoolant  @lstein  
+/invokeai/frontend @blessedcoolant  @lstein  @dunkeroni  
 
 # generation, model management, postprocessing
-/invokeai/backend  @lstein @blessedcoolant     
+/invokeai/backend  @lstein @blessedcoolant @dunkeroni @JPPhoto
 
 # front ends
 /invokeai/frontend/CLI @lstein  
 /invokeai/frontend/install @lstein   
 /invokeai/frontend/merge @lstein @blessedcoolant  
 /invokeai/frontend/training @lstein @blessedcoolant  
-/invokeai/frontend/web  @blessedcoolant  @lstein
+/invokeai/frontend/web  @blessedcoolant  @lstein @dunkeroni @Pfannkuchensack 
 

.github/workflows/mkdocs-material.yml

@@ -22,12 +22,12 @@ jobs:
 
     steps:
       - name: checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: setup python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: '3.10'
+          python-version: '3.12'
           cache: pip
           cache-dependency-path: pyproject.toml
 

docs/installation/quick_start.md

@@ -31,6 +31,12 @@ Hardware requirements vary significantly depending on model and image output siz
         - Memory: At least 32GB RAM.
         - Disk: 10GB for base installation plus 200GB for models.
 
+    === "Z-Image Turbo - 1024x1024"
+        - GPU: Nvidia 20xx series or later, 8GB+ VRAM for the Q4_K quantized model. 16GB+ needed for the Q8 or BF16 models.
+        - Memory: At least 16GB RAM.
+        - Disk: 10GB for base installation plus 35GB for models.
+
+
 More detail on system requirements can be found [here](./requirements.md).
 
 ## Step 2: Download and Set Up the Launcher

docs/installation/requirements.md

@@ -31,6 +31,11 @@ The requirements below are rough guidelines for best performance. GPUs with less
         - Memory: At least 32GB RAM.
         - Disk: 10GB for base installation plus 200GB for models.
 
+    === "Z-Image Turbo - 1024x1024"
+        - GPU: Nvidia 20xx series or later, 8GB+ VRAM for the Q4_K quantized model. 16GB+ needed for the Q8 or BF16 models.
+        - Memory: At least 16GB RAM.
+        - Disk: 10GB for base installation plus 35GB for models.
+
 !!! info "`tmpfs` on Linux"
 
     If your temporary directory is mounted as a `tmpfs`, ensure it has sufficient space.

invokeai/app/invocations/flux_denoise.py

@@ -47,6 +47,7 @@
     pack,
     unpack,
 )
+from invokeai.backend.flux.schedulers import FLUX_SCHEDULER_LABELS, FLUX_SCHEDULER_MAP, FLUX_SCHEDULER_NAME_VALUES
 from invokeai.backend.flux.text_conditioning import FluxReduxConditioning, FluxTextConditioning
 from invokeai.backend.model_manager.taxonomy import BaseModelType, FluxVariantType, ModelFormat, ModelType
 from invokeai.backend.patches.layer_patcher import LayerPatcher
@@ -63,7 +64,7 @@
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="4.1.0",
+    version="4.2.0",
 )
 class FluxDenoiseInvocation(BaseInvocation):
     """Run denoising process with a FLUX transformer model."""
@@ -132,6 +133,12 @@ class FluxDenoiseInvocation(BaseInvocation):
     num_steps: int = InputField(
         default=4, description="Number of diffusion steps. Recommended values are schnell: 4, dev: 50."
     )
+    scheduler: FLUX_SCHEDULER_NAME_VALUES = InputField(
+        default="euler",
+        description="Scheduler (sampler) for the denoising process. 'euler' is fast and standard. "
+        "'heun' is 2nd-order (better quality, 2x slower). 'lcm' is optimized for few steps.",
+        ui_choice_labels=FLUX_SCHEDULER_LABELS,
+    )
     guidance: float = InputField(
         default=4.0,
         description="The guidance strength. Higher values adhere more strictly to the prompt, and will produce less diverse images. FLUX dev only, ignored for schnell.",
@@ -242,6 +249,12 @@ def _run_diffusion(
             shift=not is_schnell,
         )
 
+        # Create scheduler if not using default euler
+        scheduler = None
+        if self.scheduler in FLUX_SCHEDULER_MAP:
+            scheduler_class = FLUX_SCHEDULER_MAP[self.scheduler]
+            scheduler = scheduler_class(num_train_timesteps=1000)
+
         # Clip the timesteps schedule based on denoising_start and denoising_end.
         timesteps = clip_timestep_schedule_fractional(timesteps, self.denoising_start, self.denoising_end)
 
@@ -426,6 +439,7 @@ def _run_diffusion(
                 img_cond=img_cond,
                 img_cond_seq=img_cond_seq,
                 img_cond_seq_ids=img_cond_seq_ids,
+                scheduler=scheduler,
             )
 
         x = unpack(x.float(), self.height, self.width)

invokeai/app/invocations/metadata_linked.py

@@ -52,6 +52,7 @@
 )
 from invokeai.app.invocations.scheduler import SchedulerOutput
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField, T2IAdapterInvocation
+from invokeai.app.invocations.z_image_denoise import ZImageDenoiseInvocation
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.model_manager.taxonomy import BaseModelType, ModelType, SubModelType
 from invokeai.backend.stable_diffusion.schedulers.schedulers import SCHEDULER_NAME_VALUES
@@ -729,6 +730,52 @@ def _loras_to_json(obj: Union[Any, list[Any]]):
         return LatentsMetaOutput(**params, metadata=MetadataField.model_validate(md))
 
 
+@invocation(
+    "z_image_denoise_meta",
+    title=f"{ZImageDenoiseInvocation.UIConfig.title} + Metadata",
+    tags=["z-image", "latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
+    category="latents",
+    version="1.0.0",
+)
+class ZImageDenoiseMetaInvocation(ZImageDenoiseInvocation, WithMetadata):
+    """Run denoising process with a Z-Image transformer model + metadata."""
+
+    def invoke(self, context: InvocationContext) -> LatentsMetaOutput:
+        def _loras_to_json(obj: Union[Any, list[Any]]):
+            if not isinstance(obj, list):
+                obj = [obj]
+
+            output: list[dict[str, Any]] = []
+            for item in obj:
+                output.append(
+                    LoRAMetadataField(
+                        model=item.lora,
+                        weight=item.weight,
+                    ).model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
+                )
+            return output
+
+        obj = super().invoke(context)
+
+        md: Dict[str, Any] = {} if self.metadata is None else self.metadata.root
+        md.update({"width": obj.width})
+        md.update({"height": obj.height})
+        md.update({"steps": self.steps})
+        md.update({"guidance": self.guidance_scale})
+        md.update({"denoising_start": self.denoising_start})
+        md.update({"denoising_end": self.denoising_end})
+        md.update({"scheduler": self.scheduler})
+        md.update({"model": self.transformer.transformer})
+        md.update({"seed": self.seed})
+        if len(self.transformer.loras) > 0:
+            md.update({"loras": _loras_to_json(self.transformer.loras)})
+
+        params = obj.__dict__.copy()
+        del params["type"]
+
+        return LatentsMetaOutput(**params, metadata=MetadataField.model_validate(md))
+
+
 @invocation(
     "metadata_to_vae",
     title="Metadata To VAE",

invokeai/app/invocations/pbr_maps.py

@@ -0,0 +1,59 @@
+import pathlib
+from typing import Literal
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.fields import ImageField, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.pbr_maps.architecture.pbr_rrdb_net import PBR_RRDB_Net
+from invokeai.backend.image_util.pbr_maps.pbr_maps import NORMAL_MAP_MODEL, OTHER_MAP_MODEL, PBRMapsGenerator
+from invokeai.backend.util.devices import TorchDevice
+
+
+@invocation_output("pbr_maps-output")
+class PBRMapsOutput(BaseInvocationOutput):
+    normal_map: ImageField = OutputField(default=None, description="The generated normal map")
+    roughness_map: ImageField = OutputField(default=None, description="The generated roughness map")
+    displacement_map: ImageField = OutputField(default=None, description="The generated displacement map")
+
+
+@invocation("pbr_maps", title="PBR Maps", tags=["image", "material"], category="image", version="1.0.0")
+class PBRMapsInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Generate Normal, Displacement and Roughness Map from a given image"""
+
+    image: ImageField = InputField(description="Input image")
+    tile_size: int = InputField(default=512, description="Tile size")
+    border_mode: Literal["none", "seamless", "mirror", "replicate"] = InputField(
+        default="none", description="Border mode to apply to eliminate any artifacts or seams"
+    )
+
+    def invoke(self, context: InvocationContext) -> PBRMapsOutput:
+        image_pil = context.images.get_pil(self.image.image_name, mode="RGB")
+
+        def loader(model_path: pathlib.Path):
+            return PBRMapsGenerator.load_model(model_path, TorchDevice.choose_torch_device())
+
+        torch_device = TorchDevice.choose_torch_device()
+
+        with (
+            context.models.load_remote_model(NORMAL_MAP_MODEL, loader) as normal_map_model,
+            context.models.load_remote_model(OTHER_MAP_MODEL, loader) as other_map_model,
+        ):
+            assert isinstance(normal_map_model, PBR_RRDB_Net)
+            assert isinstance(other_map_model, PBR_RRDB_Net)
+            pbr_pipeline = PBRMapsGenerator(normal_map_model, other_map_model, torch_device)
+            normal_map, roughness_map, displacement_map = pbr_pipeline.generate_maps(
+                image_pil, self.tile_size, self.border_mode
+            )
+
+            normal_map = context.images.save(normal_map)
+            normal_map_field = ImageField(image_name=normal_map.image_name)
+
+            roughness_map = context.images.save(roughness_map)
+            roughness_map_field = ImageField(image_name=roughness_map.image_name)
+
+            displacement_map = context.images.save(displacement_map)
+            displacement_map_field = ImageField(image_name=displacement_map.image_name)
+
+        return PBRMapsOutput(
+            normal_map=normal_map_field, roughness_map=roughness_map_field, displacement_map=displacement_map_field
+        )