Sign In

Pony Diffusion V5

658
9.9k
96
Verified:
SafeTensor
Type
Checkpoint Trained
Stats
6,354
Reviews
Published
Oct 31, 2023
Base Model
SD 2.1 768
Training
Epochs: 20
Hash
AutoV2
6FDB703D7D

Pony Diffusion V5 is a western cartoon style SD 2.1 768px finetune capable of producing stunning SFW and NSFW visuals of various anthro or feral species, humanoids and their interactions based on simple natural language prompts.

Please join our Discord Server to support development of new versions of this model and get access to free SD bot and check out more examples of this model capabilities on our prompt sharing website or follow the author on Twitter.

Important information

You will need to use either --xformers or --no-half (super slow) to load this model, I am not entirely sure why this is necessary yet.

This model supports a wide array of styles and aesthetics but provides an opinionated default prompt template that allows generation of high quality samples with no negative prompt and otherwise default settings

score_9, just describe what you want, tag1, tag2

which can be further refined with negative prompt of

watercolor painting, brush strokes

if you prefer "soft shading" style.

You may also specify whether you want no background as by default the model tends to put characters in scenic floral environments.

Other special data selection tags include, 'source_pony', 'source_furry', 'source_cartoon' and 'source_anime' and ratings of 'score_safe', 'score_questionable' and 'score_explicit'.

This model is capable of recognizing many popular and obscure characters and series.

If you are looking specifically for pony style, I recommend using one of the two following templates `anthro/feral pony, rest of the prompt` or `source_pony, rest of the prompt`.

This model is very capable of understanding of natural language so just describing intended result works in most cases, although you can add some tags after the main prompt to boost them.

One side effect of this, is that if you rely only on tags, you may want to add 'solo' as otherwise the prompt may be interpreted as multiple character, i.e.

cute pony, fancy pony, solo (without solo you will get a cute pony and a fancy pony)

Using Euler a with 35 steps and resolution of 768px is recommended although model generally can go up to 1024 as long as one of the sides is kept at 768px. Please use Waifu Diffusion VAE.

Special thanks

  • Iceman for helping to procure necessary training resources

  • Haru for assistance with captioning efforts

  • Cookie for technical expertise in training

  • PSAI Server Subscribers for supporting the project costs

  • PSAI Server Moderators for being vigilant and managing the community

Technical details

The model has been trained on ~1.3M images aesthetically ranked based on authors personal preferences, with roughly 1:1 ratio between anime/cartoon/furry/pony datasets and 1:1 ratio between safe/questionable/explicit ratings. About 25% of all images has been captioned with high quality detailed captions, which results in very strong natural language capabilities.

All images has been trained with both captions (when available) and tags, artists' names have been removed and source data has been filtered based on our Opt-in/Opt-out program. Any explicit content involving underage characters has been filtered out.

License

This model is licensed under a modified Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/) license.

The following modifications have been added to Fair AI Public License:

You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges.

If you want to use this model commercially, please reach us at [email protected].

Explicit permission for inference has been granted to CivitAi and Hugging Face.