47 lines
2.8 KiB
Markdown
47 lines
2.8 KiB
Markdown
# SD-Latent-Interposer
|
|
A small neural network to provide interoperability between the latents generated by the different Stable Diffusion models.
|
|
|
|
I wanted to see if it was possible to pass latents generated by the new SDXL model directly into SDv1.5 models without decoding and re-encoding them using a VAE first.
|
|
|
|
## Installation
|
|
To install it, simply clone this repo to your custom_nodes folder using the following command: `git clone https://github.com/city96/SD-Latent-Interposer custom_nodes/SD-Latent-Interposer`.
|
|
|
|
Alternatively, you can download the [comfy_latent_interposer.py](https://github.com/city96/SD-Latent-Interposer/raw/main/comfy_latent_interposer.py) file to your `ComfyUI/custom_nodes` folder as well. You may need to install hfhub using the command `pip install huggingface-hub` inside your venv.
|
|
|
|
If you need the model weights for something else, they are [hosted on HF](https://huggingface.co/city96/SD-Latent-Interposer/tree/main) under the same Apache2 license as the rest of the repo.
|
|
|
|
## Usage
|
|
See the image below for an example on how to use it. xl=>v1 conversion is almost flawless, **v1=>xl seems to produce artifacts.**
|
|
|
|
|
|
|
|
Without the interposer, the two latent spaces are incompatible:
|
|
|
|
|
|
|
|
## Training
|
|
The training script should spit out a working model, nn layout is probably not optimal but I'm pretty short on VRAM to trial and error a better layout. PRs welcome.
|
|
|
|
### Interposer v1.1
|
|
This is the second release using the "spaceship" architecture. It was trained on the Flickr2K dataset and was continued from the v1.0 checkpoint.
|
|
Overall, it seems to perform a lot better, especially for real life photos. I also investigated the odd v1->xl artifacts but in the end it seems [inherent to the VAE decoder stage.](https://github.com/comfyanonymous/ComfyUI/issues/1116)
|
|
|
|
|
|
|
|
### Interposer v1.0
|
|
Not sure why the training loss is so different, it might be due to the """highly curated""" dataset of 1000 random images from my Downloads folder that I used to train it.
|
|
|
|
I probably should've just grabbed LAION.
|
|
|
|
I also trained a v1-to-v2 mode, before realizing v1 and v2 shared the same latent space. Oh well.
|
|
|
|
<details>
|
|
<summary>Loss graphs for v1.0 models</summary>
|
|
|
|
|
|
|
|
|
|
|
|
</details>
|
|
|