Shared model instances across TinyTxtToImg objects for efficiency
Added option to unload models from memory
Improved CUDA and CPU memory handling
Introduced ScaleLatentChannelwise for latent scaling
Added TextInImage and DetectTextLines for OCR capabilities
Removed unnecessary comments and adjusted code formatting
updated openai and openai_function_calling using:
pip install --upgrade {package name}
found a missing RETURN_TYPES = ("IMAGE",) in ETKLGN/image.PreviewImageTest
This commit adds several new nodes to enable flexible typing and conversion between types:
- ValueToAny - Converts primitive values like ints, floats, strings, bools to Any type
- IterableToAny - Converts iterable values like lists, dicts to Any
- CallableToAny - Converts callables like functions to Any
- ObjectToAny - Converts tensor objects like images, latents etc to Any
The motivation is to allow passing different types flexibly into functions using Any typing. This enables writing functions in a more generic way by accepting Any instead of specific types.
The nodes convert the input values to Any and return debug info on what was converted. This allows tracing what types entered a function even if the function uses generic Any types.
No breaking changes, new nodes added:
- ValueToAny
- IterableToAny
- CallableToAny
- ObjectToAny
These provide building blocks for more flexible typing, opening up possibilities like:
- Writing utility and processing functions accepting Any instead of specific types
- Calling functions dynamically with values of different types
- Tracing and logging what types passed through a function
Next steps could include AnyToValue nodes, more specialized Any converters, and exploring uses for generic functions.
started creating whisper transcription node
modified how imports are handled to avoid importing the same moduels twice under different name spaces.
added basic.py to house simple functions that work on primitives.
NOTE: this update relies on change to /web/extensions that are not included in this commit, a future commit will include an install process for these changes.
This commit refactors the handling of the 'steps' attribute, making it configurable via arguments, and adds memory cleanup logic within the 'stackme' method. Additionally, conditional cloning of images ensures that operations are performed only if the images are not None. Commented-out code provides a placeholder for potential future modifications.
- DecodeTranscriptNode to parse transcript text
- YoutubeUploadNode to upload videos to YouTube
- Audio metadata and file list nodes
- Image stack blending and stripping alpha channel
- Sampler dataset creation node
- Utils for deep copying tensors and arrays
Also includes:
- Testing for new utils module
- Git nodes marked with base class
- Renamed nodes.py to avoid conflicts
- Import refactoring to handle naming
Specifics:
- descript.py: New transcript parsing node
- youtube_nodes.py: New YouTube upload node
- audio.py: New audio metadata and file list nodes
- utils.py: Deep copy utility functions
- image.py: New image stack blending and alpha stripping
- tests/test_utils.py: Tests for new utils
- git.py: Marked git nodes with base class
- __init__.py: Refactored imports and mappings
- requirements.txt: Added YouTube dependencies
- functional.py: Minor tweaks
- modules/youtube.py: Helper for upload node
- video.py: Minor cleanup
- tests/test_youtube_nodes.py: Test for YouTube upload
# Context:
USER: add `image.py`
ASSISTANT: Sure, I can help with that. However, I need more information about what you want to include in `image.py`. Could you please provide more details?
USER: I need you to use it so you can understand the framework
ASSISTANT: I understand that you want me to create a new file named `image.py`. However, without specific details about what this file should contain, I can only provide a basic template. Here's a simple Python file structure:
```python
image.py
<<<<<<< ORIGINAL
=======
# This is a new file named image.py
def main():
pass
if __name__ == "__main__":
main()
>>>>>>> UPDATED
```
Please provide more details if you need specific functions or classes in this file.
- This test validates the functionality of the `TemporalSpatialSmoothing` handler, which smooths image stacks in both temporal and spatial dimensions.
- The test uses random frames of noise and verifies the correctness of the handler.
- Made minor changes in `image.py`
- Updated code formatting for improved readability and consistency.
- Added error handling for cases when creating a PIL image from a numpy array.
- No significant changes were made in `video.py`.
These changes primarily focus on adding test coverage and maintaining code quality.
Tasha Upchurch