- Applied the noise interpolation method from the paper "Improving Image Fidelity in Image-to-Video Generation using Noise Interpolation" (https://arxiv.org/pdf/2403.02827.pdf) to achieve high source image fidelity in I2V generation.
- Integrated the technique into our pipeline to enhance source image information during early denoising steps, leading to improved video output quality.
- Referenced and adapted the approach from the implementation available at https://noise-rectification.github.io/.
controls the fidelity and diversity of the generated images. denoise_strength is typically used
in models like diffusion models or similar generative models. It influences the balance between preserving image
details and achieving diversity during the generation process. A higher denoise strength means the image will
be closer to real images from the training data, while a lower denoise strength may retain more noise,
leading to more abstract or creative results
- Redesigned code nodes based on `kijai/ComfyUI-CogVideoXWrapper` to adhere to ComfyUI standards.
- Refactored CogVideoXPipeline operations to align with standard latents processing.
- Updated node class mappings and implemented necessary changes for seamless integration.
