diff --git a/README.md b/README.md
index 18a3d8a..86a0dbd 100644
--- a/README.md
+++ b/README.md
@@ -4,14 +4,17 @@ A small neural network to provide interoperability between the latents generated
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`.
+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.
+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. The current files are in the **"v4.0"** subfolder.
## 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.**
+Simply place it where you would normally place a VAE decode followed by a VAE encode. Set the denoise as appropirate to hide any artifacts while keeping the composition. See image below.
@@ -20,14 +23,53 @@ Without the interposer, the two latent spaces are incompatible:
### Local models
-The node pulls the required files from huggingface hub by default. You can create a `models` folder and place the modules there if you have a flaky connection or prefer to use it completely offline. The custom node will prefer local files over HF when available. The path should be: `ComfyUI/custom_nodes/SD-Latent-Interposer/models`
+The node pulls the required files from huggingface hub by default. You can create a `models` folder and place the models there if you have a flaky connection or prefer to use it completely offline. The custom node will prefer local files over HF when available. The path should be: `ComfyUI/custom_nodes/SD-Latent-Interposer/models`
-Alternatively, just clone the entire HF repo to it: `git clone https://huggingface.co/city96/SD-Latent-Interposer custom_nodes/SD-Latent-Interposer/models`
+Alternatively, just clone the entire HF repo to it:
+```
+git clone https://huggingface.co/city96/SD-Latent-Interposer custom_nodes/SD-Latent-Interposer/models
+```
+
+### Supported Models
+
+Model names:
+
+| code | name |
+| ---- | -------------------------- |
+| `v1` | SDXL |
+| `xl` | Stable Diffusion v1.x |
+| `ca` | Stable Cascade (Stage A/B) |
+
+Available models:
+
+| From | to `v1` | to `xl` | to `ca` |
+|:----:|:-------:|:-------:|:-------:|
+| `v1` | - | v4.0 | No |
+| `xl` | v4.0 | - | No |
+| `ca` | v4.0 | v4.0 | - |
## Training
-Most of the training/preprocessing code is a 1:1 mirror from my latent upscaler. The folder layout it expects is also the same.
+
+The training code initializes most training parameters from the provided config file. The dataset should be a single .bin file saved with `torch.save` for each latent version. The format should be [batch, channels, height, width] with the "batch" being as large as the dataset, ie 88000.
+
+### Interposer v4.0
+
+The training code currently initializes two copies of the model, one in the target direction and one in the opposite. The losses are defined based on this.
+
+- `p_loss` is the main criterion for the primary model.
+- `b_loss` is the main criterion for the secondary one.
+- `r_loss` is the output of the primary model back through the secondary model and checked against the source latent (basically a round trip through the two models).
+- `h_loss` is the same as `r_loss` but for the secondary model.
+
+All models were trained for 50000 steps with either batch size 128 (xl/v1) or 48 (cascade).
+The training was done locally on an RTX 3080 and a Tesla V100S.
+
+### Older versions
+
+Interposer v3.1
### Interposer v3.1
+
This is basically a complete rewrite. Replaced the mediocre bunch of conv2d layers with something that looks more like a proper neural network. No VGG loss because I still don't have a better GPU.
Training was done on combined Flickr2K + DIV2K, with each image being processed into 6 1024x1024 segments. Padded with some of my random images for a total of 22,000 source images in the dataset.
@@ -38,7 +80,7 @@ v3.0 was 500k steps at a constant LR of 1e-4, v3.1 was 1M steps using a CosineAn
-### Older versions
+Interposer v1.1
@@ -50,6 +92,7 @@ Overall, it seems to perform a lot better, especially for real life photos. I al
Interposer v1.0
### Interposer v1.0