SDXL

NinjaFusion Real PDXL

NinjaFusion Real PDXL - AI Model cover image
Uploaded at
Oct 19, 2024, 10:32 AM
Uses
5.1k
Reviews
Satisfactory  (1)
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Description

https://civitai.com/models/859275 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.

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 as that might be one of the best SDXL/Pony checkpoints ever released. You very much might prefer that one over mine.

That model is incredible (including others that I used) and 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, the model is a result of some random values I tried and I really don't have much of an idea of what I'm exactly doing. Still, the results are great. For a model with the creator having much better knowledge and idea of what he's making, refer to the TAME Pony model that I linked above. I'm just throwing darts blindfolded and hoping it'll stick.

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.

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 as the upscale model.

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

As of now, this model is a merge that uses the following models in arbitrary ratios (credits to the creators): TAME Pony v2 (Base)

SnowPony v1

WAI-ANI-NSFW-PONYXL v8

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

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

Do tell me if the early access bothers anyone too much, and I'll try to remove it if it hasn't already gathered enough buzz.

Comments