title: boring_e621
tags:
- textual inversion embeddings
- image-generation
license: apache-2.0
boring_e621
This embedding attempts to capture what it means for an image to be uninteresting. It was trained as a negative embedding using e621 style tags as prompts during training.
If you're using the Automatic1111 Stable Diffusion WebUI, place the boring_e621_v4.pt file in
stable-diffusion-webui\embeddings and add "boring_e621_v4" to your negative prompt for more interesting outputs.
Model Description
The motivation for boring_e621 is that negative embeddings like Bad Prompt, whose training is described here depend on manually curated lists of tags describing features people do not want their images to have, such as "deformed hands". Some problems with this approach are:
- Manually compiled lists will inevitably be incomplete.
- Models might not always understand the tags well due to a dearth of training images labeled with these tags.
- It can only capture named concepts. If there exist unnamed yet visually unappealing concepts that just make an image look wrong, but for reasons that cannot be succinctly explained, they will not be captured by a list of tags.
To address these problems, boring_e621 employs textual inversion on a set of images automatically extracted from the art site
e621.net, a rich resource of millions of hand-labeled artworks, each of which is both human-labeled topically and rated
according to its quality. E621.net allows users to express their approval of an artwork by either up-voting it, or marking it as a favorite.
Boring_e621 was specifically trained artworks automatically selected from the site according to the criteria
that no user has ever Favorited or Up-Voted them. boring_e621 thus learned to produce low-quality images, so when it is
used in the negative prompt of a stable diffusion image generator, the model avoids making mistakes that would make the generation more boring.
Bias, Risks, and Limitations
- Using this as a negative embedding often sacrifices some fidelity to the prompt. For example, characters in the image may disappear or change eye/skin color.
- Using this as a negative embedding may introduce unexpected or undesired content into the image to make it look less boring.
- Unlike other negative embeddings, this is not intended to fix problems like extra limbs or deformed hands. It can be used alongside other negative embeddings to fix deformities.
Evaluation
To qualitatively evaluate how well boring_e621 has learned to improve image quality, we apply it to 4 simple sample prompts using the base Stable Diffusion 1.5 model.
As we can see, putting these embeddings in the negative prompt yields a more delicious burger, a more vibrant and detailed landscape, a prettier pharoah, and a more 3-d-looking aquarium.
Other Models
Boring_e621 has been reported to work well with SD 1.4 or 1.5 models such as:
- https://civitai.com/models/18208?modelVersionId=68551
- https://civitai.com/models/12979/lawlass-yiffymix-20-furry-model
- https://civitai.com/models/4698/lawlass-yiff-mix
- https://civitai.com/models/15503/kavka-mix
- https://civitai.com/models/17649/bb95-furry-mix
- https://huggingface.co/Doubleyobro/yiffy-e18 . This was the fine-tuned model used to train boring_e621.