SD-Latent-Upscaler
SD-Latent-Upscaler copied to clipboard
city96
Upscaling stable diffusion latents using a small neural network.
Not sure what your training process is however were you training with the actual 1.0 vae? or did you use the 0.9 vae? - it's known that an "invisible" (quite...
We are working with dr.lt.data and comfyanon to build a global registry for custom nodes (similar to PyPI). Eventually, the registry will be used as a backend for the UI-manager....
This PR adds a Github Action (publish-node-action) that will run whenever the pyproject.toml file changes. The pyproject.toml defines the custom node version you want to publish (added in another PR)....
I have a project for which I would need latent downscaling or resizing. If you have everything set up, could you quickly train a downscaler from 128x128x4 to 64x64x4 for...
Is there a way to adapt this technology to FLUX 1.dev models? Currently it is not possible to use these nodes for FLUX due to the size difference VAE. Thanks...
First: thank you for your work on this extension! It's pretty great. Would you consider moving the default location for model downloads to the standard `ComfyUI/models` directory, instead of `ComfyUI/custom_nodes/SD-Latent-Upscaler/models`...
Hi, First, thank you for creating such a game-changing tool. Its power is immense, but let's be honest: the vast ocean of custom nodes can be intimidating for many. We...
Can such a study specific to the FLUX1 model be applied? Can we adapt this study to the flux1 model?
