Pony Diffusion V6 XL

🚀 Pony_Diffusion_V6_XL

A versatile SDXL finetune for generating stunning SFW and NSFW visuals of various species.

🚀 Quick Start

To trigger the image generation, you should use None. The weights for this model are available in Safetensors format. You can Download them in the Files & versions tab.

✨ Features

• Versatile Visual Generation: Pony Diffusion V6 is capable of producing stunning SFW and NSFW visuals of various anthro, feral, or humanoids species and their interactions based on simple natural language prompts.
• Wide Style Support: It supports a wide array of styles and aesthetics and provides an opinionated default prompt template that allows generation of high - quality samples with no negative prompt and otherwise default settings.
• Character and Series Recognition: The model can recognize many popular and obscure characters and series.
• Natural Language Understanding: Trained on a combination of natural language prompts and tags, it can understand both, enabling users to describe the intended result using normal language in most cases.

📚 Documentation

Model Description

Pony Diffusion V6 is a versatile SDXL finetune. It can generate various visuals based on simple natural language prompts.

CHECK "ABOUT THIS VERSION" ON THE RIGHT IF YOU ARE NOT ON "V6" FOR IMPORTANT INFORMATION.

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:

• Make sure you load this model with clip skip 2 (or - 2 in some software), otherwise you will be getting low - quality blobs.
• The model supports a wide array of styles and aesthetics. Its default prompt template is score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, just describe what you want, tag1, tag2. (Previous Pony Diffusion models used a simpler score_9 quality modifier. The longer version in V6 XL is a training issue that was too late to correct during training. You can still use score_9, but it has a much weaker effect compared to the full string. You can learn more about these tags here).
• The model is designed to not need negative prompts in most cases and does not need other quality modifiers like "hd", "masterpiece", etc.
• Other special data selection tags include source_pony, source_furry, source_cartoon, source_anime, and ratings of rating_safe, rating_questionable, and rating_explicit.
• If you are looking specifically for pony style, it is recommended to use one of the two following templates anthro/feral pony, rest of the prompt or source_pony, rest of the prompt.
• The model is trained on a combination of natural language prompts and tags and can understand both. You can describe the intended result using normal language, and you can add some tags after the main prompt to boost the result.
• Using Euler a with 25 steps and a resolution of 1024px is recommended, although the model generally can support most SDXL resolutions.
• This model will sometimes generate pseudo - signatures that are hard to remove even with negative prompts. This is a training issue that will be corrected in future models. If that's an issue for you, I suggest trying V5.5 or inpainting.

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 ~2.6M images aesthetically ranked based on the author's personal preferences, with roughly a 1:1 ratio between anime/cartoon/furry/pony datasets and a 1:1 ratio between safe/questionable/explicit ratings. About 50% of all images have been captioned with high - quality detailed captions, which results in very strong natural language capabilities.

All images have 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 the 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 contact@purplesmart.ai.

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

Source

https://civitai.com/models/257749

Credit

https://civitai.com/user/PurpleSmartAI

Trigger Words

You should use None to trigger the image generation.

Download Model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

Information Table

Important Notes

⚠️ Important Note

Make sure you load this model with clip skip 2 (or -2 in some software), otherwise you will be getting low quality blobs. This model will sometimes generate pseudo signatures that are hard to remove even with negative prompts. This is a training issue that will be corrected in future models. If that's an issue for you, I suggest trying V5.5 or inpainting.

💡 Usage Tip

Using Euler a with 25 steps and a resolution of 1024px is recommended, although the model generally can support most SDXL resolutions. If you are looking specifically for pony style, use one of the two following templates anthro/feral pony, rest of the prompt or source_pony, rest of the prompt.