Yes, we have Pony! (now on version 2!)

Available at YODAYO.

The concept behind this model is to allow YOU to have the widest range of features with a single model. I'm happy to present the PONY XL model of the ONE FOR ALL series!!!

☕ I LOVE COFEE!! Want to buy me a cup?? ☕

Other ways to help me: Instagram (follow me)

PLEASE, if you like the model, share your work, and share the model, please.

It's worth mentioning that despite using a proprietary training model as a base, this version incorporates other trained models. Therefore, it classifies as a Merge rather than a Fully Trained model.

Prompt Recommendations (please read!!):

Despite using the Pony Diffusion V6 XL model as a base, this checkpoint is a legitimate ONE FOR ALL, so adherence to the prompts is always an important factor along with quality.

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 supports a wide array of styles and aesthetics but provides an opinionated default prompt template that allows generation of high quality samples with no negative prompt and otherwise default settings

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, just describe what you want, tag1, tag2

BUT REMEMBER, IT HAS DPO TOO, keep that in mind if you don't get the result you want.

AVOID USING ABSTRACT CONCEPTS LIKE POEMS OR MUSICS!!

If you want to use poems, music, etc, use: ONE FOR ALL «Plus Ultra» - v 3 DPO+Pony

ONE FOR ALL + PONY PROMPTS EXAMPLES FOR VERSION 2:

Steps: (70), Sampler: (dpmpp_3m_sde_gpu)
CFG scale: (8.0, 8.0), Add noise: disable, Seed: 580662435536181
Size: 1024x1024, Model: (ONE FOR ALL «Pony Fantasy» v. 2 DPO.bf16
Scheduler: (exponential), Start at step: 80, End at step: 10000
Denoise: 1.0

Prompt:

girl

Individual difference score from 4 to 10

Score group difference from 9 to 4 in individual descending order, followed by the difference in ascending order from score 4 and 5, followed by 4, 5, 6 and 7 and finally the total combination:

Source representation:

Some prompts with additional effects:

FAST Q&A:

Q: My generation never come as source_anime, how to get a flat anime style?

A: Try to remove all the score tags. It will make the AI uses the anime style by default. If even with that, you still didn't get the flat style, check your prompt if it doesn't have something like 'realistic' on it. Finally add photo, realistic in the negative prompt.

Q: Why I always get NSFW images even using rating_safe?

A: It happens because version 2 is supposed to give more weight to NSFW. The options here are, remove the score_4_up from your prompt, add score_4 on negative. If it doesn't work, check your prompt for NSFW tags. Finally set more weight to the rating, like: (rating_safe:1.4).

Q: How to get a more realistic image?

A: First, have sure to use source_photo on your prompt, secondly add (photography, realistic:1.4) check the result. Still not there? Try to add (anime, cartoon, 2D, 2.5D, digital) in the negative prompt.

Q: The colors and style are weird, how to fix?

A: Have sure that your prompt don't have oblique or conflict in styles etc. But, I bet your prompt have HDR on it. 😅😅😅 The AI will take it to another level, I probably messed something, sorry about that, take the HDR off.

Q: You said your model should make vibrant colors, but it still look like all other pony models around, are you trying to fooling us around?

A: NO!! lol, ok, maybe. J/K!! Ok, the thing is, score_ is like a wildcard, so it has information about quality and other things. Once we merge the original Pony to make our models we need to pay attention on some aspects. In «Pony Fantasy» for example, I have an own model merged. The sum of the checkpoints ends up altering some factors. In short, my suggestion is to remove ALL Score_ except score_8 (without _up). This should bring out a brighter color. I recommend that you run tests with the scores, you may end up discovering some very interesting things.

If you have any question or issue, please contact me. If you want to get the best and the max from the «Pony Fantasy», look here: Danbooru Tagging Visualization for PonyXL

ONE FOR ALL + PONY PROMPTS EXAMPLES FOR VERSION 1:

Image posted by ChaosExperience (CLICK HERE FOR HIGH RES)

source_photo:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, photo-same-realistic upscaled-resolution, source_photo, analog photo, ultra-realism, physically-realistic, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus)
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_anime + 2.5D:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, 2.5D-upscaled-resolution, source_anime, digital-quality, semi-realism, physically-realistic, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus)
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_anime:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, anime-upscaled-resolution, source_anime, anime-quality, flat-color, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus)
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_bishoujo:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, anime-upscaled-resolution, source_bishoujo, anime-quality, flat-color, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_chibi:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, anime-upscaled-resolution, source_chibi, anime-quality, flat-color, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_mecha:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, anime-upscaled-resolution, source_mecha, anime-quality, flat-color, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_pony + furry + realistic:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, photo-same-realistic upscaled-resolution, source_pony, ultra-realistic, photo-quality, lit, cutesie, furry-characteristics)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_furry + anime:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, anime-upscaled-resolution, source_furry, anime-quality, flat-color, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_furry + realistic:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, photo-same-realistic upscaled-resolution, source_cartoon, ultra-realistic, photo-quality, lit, cutesie, furry-characteristics)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

source_pixel:

(((score_9, epic-Ultra-HD-details, epic-Ultra-HD-highlights, pixel-art-upscaled-resolution, source_pixel, lit, cutesie)))
50mm lens
aperture opening of f/4.0
(cinematic light, vivid colors like HDR+, sharp focus) 
1girl, pink hair, long hair
(delicated face, intricate details, caustic background)

Generation Recommendations/Tips:

• Sampling method:

  • DPM++ 3M SDE Exponential;

    • DPM++ 2M SDE Karras.

    • Euler

• Sampling steps:

  • 40 (The XL works differently than the SD 1.5. So the recommendation is to stay between 30 and 40).

• Width/Height:

  • Here's the big difference. If the SD 1.5 works with 512 x 512 base, the XL works with 1024 x 1024. I personally use the 1080 x 1440 resolution a lot.

• CFG Scale:

  • I use 8 as default.

    • Due to the training method and the implementation of the Pony model, low CFG can generate only noise, so if your images are only noisy, check your CFG and Steps.

PAY ATTENTION TO THE NEGATIVE PROMPT!!

As I said before, XL works differently from SD 1.5.

So start your generation without the negative prompt. That's right, start WITHOUT NEGATIVE PROMPTS. Negative prompts are very powerful in XL, so only use them when you're not getting the result you want. Don't fill up on negative prompts as many people mistakenly do in SD 1.5.

Anything beyond that depends on your taste and the results you want. 🥰

You can use my generations for reference (click here).

Thank You!! 💓💓💓

This model is only possible because there are people with incredible skills and effort. My intention at no time is to belittle any other model, on the contrary, ONE FOR ALL is an ode to these incredible people, without whom this model would not exist. Thank you very much!

If you happen to like the ONE FOR ALL series, please leave a good review and post your creations, I'll love to get to know the amazing universe you'll create! 🤩🤩🤩

If you want to thank me, like every Brazilian I love coffee, another way to encourage or thank me is to follow me on Instagram. 🥰🥰🥰

If you have any difficulties or questions, or just want to have a chat, you can contact me on Instagram or here on Civitai.

Last statements:

Please use this model for fun or work, but respect the legal regulations in force in your country and international treaties, especially regarding impersonation and pedophilia. I declare myself exempt from any violations resulting from the use of any model from the ONE FOR ALL series or its base models, being the creator of the content solely responsible.

This checkpoint (ONE FOR ALL «Plus Ultra») is not available for use outside Civitai on external generators. If you find this template running on any generation site or available for download outside Civitai, please contact me.

If you are responsible for an online generation site and would like to use any model from the ONE FOR ALL series, please contact me.

Finally, all images generated using any ONE FOR ALL model belong to their creators (user), as well as the use-fruit and responsibilities for the content created. This means, but is not limited to, the right to sell the images generated, for example.

The use of this checkpoint is conditional on acceptance of these terms.

(SP, BR, 20/01/2024)