DOGEPONY 2D:

This model should be pretty close to the original Pony V6 and you can probably recreate most of the stuff with the same seeds very closely. The main differences are: more realistic and 3D data, more anime data, less deviation/sharper, some LoRAs with unusual resolutions and the tweaked TE that might be a problem if you repeat yourself too much in the prompt.

For sampling, there's no skeleton key, try to keep awareness of the content you're trying to generate. DPM samplers paired with Karras schedulers can give you some rough, painterly shading at low steps and more realism, details at high steps, white Euler and DDPM can give you some nice flat styles and more 3D at higher steps. You can always check the showcased LoRAs prompt for details.

HiresFix and Adetailer highly recommended and used in the example pics. If you run into problems using multiple LoRAs, try toning down a bit on the weight or CFG rescale.

DOGEPONY Real:

Just be reasonable with the ammount of steps and sampler required for each character type, materials and complexity of the prompt, you can check the examples for the variety of samplers that will work well depending on what you want. Prompting should be made simple, despite solving well photorealistic things like film grain, range, different types of focus, lighting and others, in most cases, all you need is to call for the source "photo" or putting elements you don't want like "anime, cartoon, 3D" in the negative.

Should work well with most LoRAs just the 2D model and the prompting work in a very similar way. I'm open to suggestions on this model and will release some helping LoRAs for cosplayer data, amateur photography and whatever.

DOGEPONY 3D:

Not well rounded as the others, might "brainfart" on your prompts sometimes, if you're having troubles with certain words or characters, try ditching the scores. Try to be conservative around the sampling and CFG scale, some textures range are bothersome to reach

Check the examples for more info. Really like this one and will also experiment on bringing some 3D styles/concepts. Similar prompt order and LoRA compatibility as the others, would appreciate your feedback on this!

DEEPEST LORE:

I'm sorry for having you download 3 different models. Once upon a time these models were all one but due to sheer adaptative pressure issues with styles, artifacts and inconsistency, they started splitting into new species. I'm a die-hard 1.5 fan, but when I heard PONY was getting some realistic data on the update, I had to try on how it might look but all I could get was some cursed model and legend says you can still generate the most hideous wenches if you prompt for cosplay. Spooky, rite? Have fun and show me your creations!