Merge branch 'master' into dr-support-pip-cm

Author: ltdrdata

README.md

@@ -206,14 +206,32 @@ Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints
 Put your VAE in: models/vae
 
 
-### AMD GPUs (Linux only)
+### AMD GPUs (Linux)
+
 AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
 
 ```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4```
 
-This is the command to install the nightly with ROCm 6.4 which might have some performance improvements:
+This is the command to install the nightly with ROCm 7.0 which might have some performance improvements:
+
+```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.0```
+
+
+### AMD GPUs (Experimental: Windows and Linux), RDNA 3, 3.5 and 4 only.
+
+These have less hardware support than the builds above but they work on windows. You also need to install the pytorch version specific to your hardware.
+
+RDNA 3 (RX 7000 series):
+
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/```
 
-```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm6.4```
+RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):
+
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/```
+
+RDNA 4 (RX 9000 series):
+
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/```
 
 ### Intel GPUs (Windows and Linux)
 
@@ -270,12 +288,6 @@ You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS ve
 
 > **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux).
 
-#### DirectML (AMD Cards on Windows)
-
-This is very badly supported and is not recommended. There are some unofficial builds of pytorch ROCm on windows that exist that will give you a much better experience than this. This readme will be updated once official pytorch ROCm builds for windows come out.
-
-```pip install torch-directml``` Then you can launch ComfyUI with: ```python main.py --directml```
-
 #### Ascend NPUs
 
 For models compatible with Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the [installation](https://ascend.github.io/docs/sources/ascend/quick_install.html) page. Here's a step-by-step guide tailored to your platform and installation method:

comfy_api_nodes/nodes_gemini.py

@@ -39,6 +39,7 @@
     tensor_to_base64_string,
     bytesio_to_image_tensor,
 )
+from comfy_api.util import VideoContainer, VideoCodec
 
 
 GEMINI_BASE_ENDPOINT = "/proxy/vertexai/gemini"
@@ -310,7 +311,7 @@ def create_video_parts(self, video_input: IO.VIDEO, **kwargs) -> list[GeminiPart
         Returns:
             List of GeminiPart objects containing the encoded video.
         """
-        from comfy_api.util import VideoContainer, VideoCodec
+
         base_64_string = video_to_base64_string(
             video_input,
             container_format=VideoContainer.MP4,

comfy_api_nodes/nodes_moonvalley.py

@@ -2,11 +2,7 @@
 from typing import Any, Callable, Optional, TypeVar
 import torch
 from typing_extensions import override
-from comfy_api_nodes.util.validation_utils import (
-    get_image_dimensions,
-    validate_image_dimensions,
-)
-
+from comfy_api_nodes.util.validation_utils import validate_image_dimensions
 
 from comfy_api_nodes.apis import (
     MoonvalleyTextToVideoRequest,
@@ -132,47 +128,6 @@ def validate_prompts(
     return True
 
 
-def validate_input_media(width, height, with_frame_conditioning, num_frames_in=None):
-    # inference validation
-    # T = num_frames
-    # in all cases, the following must be true: T divisible by 16 and H,W by 8. in addition...
-    # with image conditioning: H*W must be divisible by 8192
-    # without image conditioning: T divisible by 32
-    if num_frames_in and not num_frames_in % 16 == 0:
-        return False, ("The input video total frame count must be divisible by 16!")
-
-    if height % 8 != 0 or width % 8 != 0:
-        return False, (
-            f"Height ({height}) and width ({width}) must be " "divisible by 8"
-        )
-
-    if with_frame_conditioning:
-        if (height * width) % 8192 != 0:
-            return False, (
-                f"Height * width ({height * width}) must be "
-                "divisible by 8192 for frame conditioning"
-            )
-    else:
-        if num_frames_in and not num_frames_in % 32 == 0:
-            return False, ("The input video total frame count must be divisible by 32!")
-
-
-def validate_input_image(
-    image: torch.Tensor, with_frame_conditioning: bool = False
-) -> None:
-    """
-    Validates the input image adheres to the expectations of the API:
-    - The image resolution should not be less than 300*300px
-    - The aspect ratio of the image should be between 1:2.5 ~ 2.5:1
-
-    """
-    height, width = get_image_dimensions(image)
-    validate_input_media(width, height, with_frame_conditioning)
-    validate_image_dimensions(
-        image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH
-    )
-
-
 def validate_video_to_video_input(video: VideoInput) -> VideoInput:
     """
     Validates and processes video input for Moonvalley Video-to-Video generation.
@@ -499,7 +454,7 @@ async def execute(
         seed: int,
         steps: int,
     ) -> comfy_io.NodeOutput:
-        validate_input_image(image, True)
+        validate_image_dimensions(image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH)
         validate_prompts(prompt, negative_prompt, MOONVALLEY_MAREY_MAX_PROMPT_LENGTH)
         width_height = parse_width_height_from_res(resolution)