Make sure that you read the generation parameters described further down in order to get to the quality of the showcase gens. No adetailer or other img2img techniques have been used for the gallery images made by me, except for one hires fix.

Short version for lower attention span:

• Use Euler A.

• Don't use karras, AYS, gits. Only SGM uniform works as intended.

• score tags are still useful, but not necessary.

This model is a result of an experimental DARE/Block merge between different Pony models. It strives to get the perfect balance between "Ponyness" and "Realism". VAE is included.

The prime objective of this series of checkpoints is to achieve the (subjective) perfect balance between the capabilities of anime models and real ones, while still retaining their individual knowledge. I will keep updating and making this checkpoint better with the experimental merging technique that I'm working on. Documentation on DARE-Ties merging of diffusion models is nonexistent and that makes this way harder to work with.

UPDATE (also changed checkpoint name): V2 should work really well in many different situations, while still maintaining a good amount of realism. The showcase images should portray the quality of the compositions and prompts that this model can handle. in general this version can do all the stuff that most popular realistic models can do, and then some. The NSFW capabilities are also far better than I could have imagined.

UPDATED Merge Recipe (not exact as I am still working with random values and iterating from there):

• Tool used: ComfyUI-DareMerge

• Base - Quintessence V1 (DARE-Ties merge between TAME Pony v2 (Base), SnowPony v1, WAI-ANI-NSFW-PONYXL v8)

  Version 2 changes -

• Merged about 15% of Illustrious x Pony Mix into different layers. The Illustrious clip has also been merged with Quintessence V1's clip using the same DARE method.

• Merged Opticon v2-rc at arbitrary but significant values I unfortunately don't remember.

The resulting newer version is more creative, and handles a more varied set of prompts and compositions.

Generation Parameters (VERY IMPORTANT):

• Only use "EULER A" with SGM UNIFORM. Nothing works better for this one, even after extensive testing.

• Use 30+ steps. Do NOT use any other scheduler apart from SGM UNIFORM. Don't use Karras or AYS or exponential. EDIT: The newer version might handle different samplers, but the scheduler still has to be SGM Uniform.

  Simple and Normal work, but SGM uniform makes the best gens.

• Hi-res fix (normal or UltimateSDUpscale) is very much recommended. Half the steps of the original gen, denoise at 0.28. Euler A + sgm_uniform again. I also recommend Ultrasharp 4x or NMKD Siax as the upscale model.

• CFG can be between 4 to 10. Use higher for more creativity, lower for more realism. I use AutomaticCFG's hard mode in ComfyUI, so I prefer CFG 9 for my gens. Normal CFG usage might vary.

Keep in mind that I am very new to this, and if you love this model make sure to check out the recommended ones. Special thanks to @zyxt99565 for making the TAME Pony checkpoint, which I used as the base for this one. Do give it a try too as that might be one of the best SDXL/Pony checkpoints ever released.

I wanted to augment some of the gritty realism it provides with a bit of the more dynamic Pony concepts according to my personal preferences. DARE merging is incredible and I experimented some stuff while making this. Thus this model was born.

But to be fair, my model is a result of some random values and experimental merging methods I tried and I really don't have much of an idea of what I'm exactly doing. Still, the results speak for themselves. I'm just throwing darts blindfolded and hoping it'll stick.

As of now, this model is a merge that uses the following models in arbitrary ratios (credits to the creators):

1. TAME Pony v2 (Base)

2. SnowPony v1

3. WAI-ANI-NSFW-PONYXL v8

4. Illustrious x Pony Mix

5. Opticon v2-rc

Also, the prompts for the showcase images have been 'borrowed' from some of the most influential models on the site. This might help you to compare the images to those models.

The clips have also been DARE merged, keeping the prompting styles from the above models consistent. Model works with both pure Pony type prompts, or a mixture of both Pony and SDXL prompting styles. Experiment yourself. I still recommend keeping the score tags in your prompts.

Until CivitAI turns on the online generation for this model, feel free to run the model here (I have no other option but to host it here, until Civit allows the model to run onsite):

RUN ONLINE

Most resolutions should work well. Feel free to discuss problems and doubts in the comments.

If you want to support the creation of more models like this, or you just like what you see: ko-fi (｡♥‿♥｡).