Suzanne's Pony

Much like Deek Dark Pony, this is both a v6 Pony model and an SDXL model. It’s a hybrid. It mixes the comprehension of both models into one that understands quite a bit but doesn’t need extra quality keywords, no scores to list, and no need to use a particular style. You can get great images from very light prompts. Prompt with Danbooru tags. Prompt with natural language. Do a combination. Use a pony prompt. Use prompts from your favorite model. Use a haiku or a dirty limerick. It doesn’t matter; the model will generally get the gist of what you are trying to tell it.

The goal was to come close to the default style of Suzanne’s XL Mix (and aesthetics of 7whitefire7’s RealCartoonXL), and like that model, Suzanne's Pony stretches from semi-realistic art to surreal, almost photographic quality. If your prompt includes more fantastical imagery, the output is more likely to lean toward semi-realistic art or even anime.  Like all Pony models, it can exaggerate anatomy but it can be controlled. Just add “realistic” to your prompt and it will push the model toward photorealism, but it’ll also often remove fantasy components to force the generation to match what’s in the real world.

Usage Tips and Prompting:

• It's basically a Turbo model, so Steps and CFG will scale. 6 to 10 Steps and a 1.5 to 3.5 CFG Scale will get you great images. If you like higher steps, you can go up to 20-30 steps and a 5-7 CFG scale. I don’t notice any returns after 30 steps.

• You can use most standard sampling methods, but SDE samplers only work with very low CFG (3 and below). It isn’t made for specialty samplers, so don’t use LMS, PLMS, DPM fast, or LCM sampling methods; it’ll generate 6 steps without anything special. I haven’t had issues with anything else.

• You don’t need a refiner, but can use one if you want a particular style. However, if your refiner doesn’t understand Pony keywords, you’ll need to go really light on the refining steps (otherwise, horrors emerge).

• If you want to use hires. fix and an upscaler, R-ESRGAN 4x+ or R-ESRGAN 4x+ Anime 6B work well with 5 or less steps and a 0.2 or less denoising strength.

• Most versions of the model are very picky about sampler settings. I typically use any of the following settings, all of which work great: DPM++ SDE Karras, DPM++ 2M Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, Euler a, DPM adaptive. Other samplers may work, but if you are getting images that don’t look fully diffused, that’s the issue.

• LoRAs: I have not done a lot of testing, but so far, Pony LoRAs work and SDXL LoRAs work. But you shouldn’t need them for anything but the most extreme poses or actions or really obscure characters.

• Prompting isn’t tricky. It’ll respond perfectly to Danbooru tags or natural language, but I’ve found that a hybrid approach works well: short natural language phrases and Danbooru tags separated by commas (at least in Automatic1111). When it comes to natural language, short and simple is the best rather than whole sentences with deep descriptions. The model runs at very low CFG values; let it fill in the details for you.

• This model is not intended to produce illegal acts and images. However, to be 100% safe, add "children, loli, child, kids, teens" to your negative prompt. Models that understand Pony prompts can be unpredictable, so safe is better than sorry.

Model Credits

The following models have been or are currently used in a version of Deep Dark Pony. Credit goes to the model creators (and, of course, the creators of the models that were used in their merges/training as well).

• RealCartoon-Pony V1 - https://civitai.com/models/618329/realcartoon-pony

• Real Dream SDXL Pony 9 - https://civitai.com/models/153568?modelVersionId=665047 

• Atomix Pony Realism XL v1.0 - https://civitai.com/models/553979/atomix-pony-realism-xl

• Imaginarium V1.0 - https://civitai.com/models/249973?modelVersionId=282087

• Suzanne's XL Mix - https://civitai.com/models/246755

• RealCartoon-XL - https://civitai.com/models/125907

• Pony Diffusion V6 XL (it wasn’t used directly, but none of this would be possible with it) - https://civitai.com/models/257749?modelVersionId=290640

Legal Stuff

AI model output may sometimes be unpredictable and is not guaranteed to match the input prompt nor to be of any given nature or quality. Do not attempt to generate content that is illegal in your legal jurisdiction or within your country or district of residence. By using this model, you agree that the creator of this model shall in no event be responsible or liable to you or to any third party, whether under contract, warranty, tort (including negligence), strict liability, indemnity or other theory, for any direct, indirect, special, incidental, consequential, exemplary, liquidated or punitive damages or any other damages, including but not limited to loss of profit, revenue or business, cost of substitute procurement, arising in whole or in part from your use of (or inability to use) the model.

Model Restrictions:

To be clear, this model is a derivative of the SDXL 1.0 model, and the following restrictions are part of the 2023 Stability AI CreativeML Open RAIL++-M License dated July 26, 2023, with applies to this model and all models that use any component or derivatives of this model. You agree not to use the Model or Derivatives of the Model:

• In any way that violates any applicable national, federal, state, local or international law or regulation; 

• For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; 

• To generate or disseminate verifiably false information and/or content with the purpose of harming others; 

• To generate or disseminate personal identifiable information that can be used to harm an individual; 

• To defame, disparage or otherwise harass others; 

• For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation; 

• For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics; 

• To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm; For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories; 

• To provide medical advice and medical results interpretation; 

• To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).

Clarifications on the permissible use of this model:

• This model is a merge. Therefore it inherits the permissions and restrictions of all models used in its creation.

• You may not make merges, extractions, or derivatives of this model and use a less restrictive license than the 2023 Stability AI CreativeML Open RAIL++-M License.

• This model may be run and hosted for download on Civitai.com. At this time, no other organization or individual is authorized to host or distribute this model.

• You may not sell this model or any of this model’s merges or derivatives.

• You must credit this model’s creator if you use this model to create a new merged, mixed, trained, or extracted model.

• You may sell images you generate with this model.

• You may share merges using this model as long as any merge has the same or more restrictive permissions.

As a derivate and or merge of Pony Diffusion XL, this model is also 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 commercial inference has been granted to CivitAi and Hugging Face.