* Added Super Resolution to the streampack
* Super Resolution created by ryan, updated for missing
* add prestartup script to check for opencv-cuda
---------
Co-authored-by: ryanontheinside <7623207+ryanontheinside@users.noreply.github.com>
Co-authored-by: John | Elite Encoder <john@eliteencoder.net>
This commit introduces a ControlNet Auxiliary Preprocessor for facial landmark
detection using MediaPipe FaceMesh. It also adds utility nodes to work with the
detected landmarks:
- Node to draw the facial mesh on an image using landmark data.
- Node to generate masks based on landmark data.
---------
Co-authored-by: ryanontheinside <ryanfosdick87@gmail.com>
This commit establishes the required file structure and logic to integrate the Feature Bank node into ComfyUI, enabling its use.
---------
Co-authored-by: RUFFY-369 <prakarshkaushik369@gmail.com>
This commit migrates the Feature Bank node, originally implemented by @RUFFY-369
on [RUFFY-369/ComfyUI-FeatureBank](https://github.com/RUFFY-369/ComfyUI-FeatureBank),
to the new streampack.
The Feature Bank node is a ComfyUI-native implementation of the method proposed in
[Looking Backward: Streaming Video-to-Video Translation with Feature Banks](https://arxiv.org/abs/2405.15757)
by Liang et al. It enhances the stream diffusion model by providing information from
previous frames, thereby improving temporal consistency and reducing flickering.
---------
Co-authored-by: RUFFY-369 <prakarshkaushik369@gmail.com>
John | Elite Encoder