Update README.md

README.md

@@ -19,8 +19,7 @@ language:
 FluffyRock Unbound is a finetune of [Fluffyrock Unleashed v1.0](https://huggingface.co/RedRocket/Fluffyrock-Unleashed) trained on an expanded, curated <a href="https://e621.net/">e621</a> dataset and with training changes adapted from Nvidia Labs <a href="https://arxiv.org/abs/2312.02696">EDM2</a>.
 
 This model can produce detailed sexually explicit content and is not suitable for use by minors.
-The model can produce non-photorealistic images of underage indivduals, animals, and non-consensual sex, but its capability to do so is more limted than other models.
-It has not been found to produce such content unless prompted to do so, and will generally not produce sexually explicit content at all unless so prompted.
+It will generally not produce sexually explicit content at all unless prompted.
 
 ## Downloads
 
@@ -28,7 +27,16 @@ It has not been found to produce such content unless prompted to do so, and will
 <a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/Fluffyrock-Unbound-v1-1.yaml?download=true">Fluffyrock-Unbound-v1-1.yaml</a> - YAML file for A1111 Stable Diffusion WebUI. Place this in the same folder as the model.<br>
 <a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/fluffyrock-unbound-tag-strength-v1.1.csv?download=true">fluffyrock-unbound-tag-strength-v1.1.csv</a> - Recommended tag completion file, representing the strength of each concept in the model. (<a href="fluffyrock-unbound-tag-strength-v1.1.csv
 ">Raw Counts</a>, <a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/fluffyrock-unbound-tag-metadata-v1.1.csv?download=true">Metadata</a>)<br>
-<a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/boring_e621_unbound_plus.safetensors?download=true">boring_e621_unbound_plus.safetensors</a> - Boring-E621 style negative embeddings to improve quality. Use in the negative prompt. (<a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/boring_e621_unbound_lite.safetensors?download=true">Lite Version</a>)
+
+### TI Embeddings
+
+<a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/boring_e621_unbound_lite.safetensors?download=true">boring_e621_unbound_lite</a>
+<a href="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/boring_e621_unbound_plus.safetensors?download=true">boring_e621_unbound_plus</a>
+
+Currently experimental textual inversion embeddings in a similar vein to the [Boring Embeddings](https://huggingface.co/FoodDesert/Boring_Embeddings).  Intended to improve quality while not drastically altering image content.  Intended to be used as part of a negative prompt (although using them in the positive prompt will work and may be even more fun).
+
+The "lite" version is 6 tokens wide and is initialized on the values of ``by <|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|>``, which is very close to a "blank slate
+The "plus" version is trained on the same dataset, is 8 tokens wide, and is initialized on an average vector of 100 low-scoring artists.  Currently, the "lite" version is recommended.
 
 ## Prompting Guide
 
@@ -41,7 +49,7 @@ Example prompt: ```solo, anthro, female, wolf, breasts, clothed, standing, outsi
 
 ## Automatic1111 Stable Diffusion WebUI Instructions
 
-### TODO
+Place the model and the corresponding .yaml file in the ``models/Stable-diffusion/`` folder.  The model will not work properly without the .yaml file.  You should also go to Settings -> Sampler Parameters and choose Zero Terminal SNR as the "Noise schedule for sampling" for ideal results.
 
 ## ComfyUI Instructions
 
@@ -60,4 +68,4 @@ The model is zero-terminal-SNR with V-prediction. Use the ModelSamplingDiscrete
 
 ## Dataset Changes
 - A sizeable overhaul of E621 tagging was done, removing several useless tags and renaming others.  We are including new tag files that represent the current state of the dataset.
-- The dataset was currated to remove hamful content, and content which was previously found to negatively impact generation quality for adjacent concepts.
+- The dataset was curated to remove harmful content that was discovered in the prior dataset, and content which was previously found to negatively impact generation quality for adjacent concepts.