Prompt Consigliati

score_9, score_8_up, score_7_up

Prompt Negativi Consigliati

use opposite keywords in the negative prompt section to enhance realism,adding some NSFW keywords combined with natural language prompts

score_6, score_5, score_4, lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs, bad art, bad painting, bad photo, bad image

Parametri Consigliati

samplers

DPM++ SDE

steps

30 - 40

cfg

9

clip skip

2

resolution

720x1280

Parametri Consigliati per Alta Risoluzione

upscaler

4xUltrasharp_4xUltrasharpV10

upscale

2

denoising strength

0.4

Suggerimenti

Adding tag_score to the prompt improves the image quality, but is not mandatory.

Use detailed and accurate prompts to get clear and precise styles or effects.

The model balances realistic and surreal/artistic effects and emphasizes 3D and realistic feeling similar to Unreal Engine graphics.

Sponsor del Creatore

If you like my content, support me at: https://ko-fi.com/duchaiten

Patreon in here:
https://linktr.ee/Duc_Haiten

If you want to use my models to create unlimited images at a small cost without installing anything, mage.space is recommended, with some exclusive models available.

Join my discord server for community and updates: https://discord.gg/FPhQvFsqe2

The model is trained on pony-no-score, but is aimed at a realistic style.

I created my discord server. I'm still quite new to discord server management, free to give opinions.

https://discord.gg/FPhQvFsqe2

you like my content, support me at:

https://ko-fi.com/duchaiten

Patreon in here:
https://linktr.ee/Duc_Haiten

If you want to use my models to create unlimited images at a small cost without having to install anything, mage.space will be a good choice, i have some models that are exclusively available on there.


Update on September 13, 2024:


Version 2.0 adds several data updates, with the most important adjustment being the shift from cool to warm colors. The lighting has also been toned down to reduce glare, making it easier to see certain details in the dark. The overall image is slightly darker, creating a more somber atmosphere when needed, but it can still be bright or warm depending on the situation.

Update on August 4, 2024:

v1.1 revised the text encoder, adjusting it so that the data should be more equal and not overlap each other.

Updated on July 5, 2024:
Finally, Pony real v1 is complete, earlier than expected since Pony v6.9 is still about 3 months away from release, so further training is no longer meaningful. I will stop and decide to wait for Pony v6.9 to be released. In the meantime, I will temporarily switch to training other models. Although the training of the Pony real model has stopped, it does not mean it has been abandoned. In fact, with a very large data source and thorough training, to some extent it can be considered another Pony base model, different from the Pony base model of PurpleSmartAI. Of course, it is not perfect; no model is perfect. Therefore, everyone can combine it with various Loras while waiting for the next updates. But I can say it is still very flexible and retains the most essential aspects of Pony, while fixing a bunch of bugs from Pony base v6.

I have worked very hard to balance between a realistic style and effects, characters, poses, anime, surreal, or anything related to art in general. It is very difficult, so sometimes I had to make some compromises. It will not be as real as photos you can freely take in real life; this model aims for the realistic feeling you get in movies that use a lot of realistic effects and ultra-realistic Unreal Engine graphics. I have also clearly defined the keywords, so you will need to type detailed and accurate prompts to get clear and precise styles or effects, or what clothes, hairstyles, etc., the characters have. I have trained it in many natural languages and separated two types of captions corresponding to two ways of typing prompts into two different clips, making it more diverse in terms of styles, prompts, and keywords. It won't follow a template, be monochromatic, or single-styled. But of course, it still focuses more on 3D and realism, because that was my initial goal

You can choose not to add tag_score to the prompt, but adding it will still make it look better.

Oh, one last thing, beautiful Asian girls are not produced on the same doll manufacturing line.

The best settings on automatic1111 are:

- Sampling method: DPM++ SDE (slow but makes the image more realistic, with fewer errors, and closer to the prompt)

- Schedule type: SGM Uniform (produces images closer to the prompt)

- CFG Scale: 9 (fewer errors)

- Sampling steps: from 30-40 (starting from step 36 onwards, the image will have more accurate details and fewer small errors. The higher the steps, the better these small details will look. However, the higher the number of steps, the more likely color errors and contrasting color patches will appear.)

Update on June 23, 2024:

Can someone please remind AstraliteHeart to quickly release pony v6.9, I want to use it to train pony real v1 and pony no score v5.

In this Beta 8 version, I improved the colors to be more vivid, with a bit of gold and cinematic depth. More artistic data is trained, improving the natural language part.

Update on June 15, 2024:

Why hasn't the model become as realistic as other pony real models so far? This is entirely intentional, or you could say that I have chosen a much more challenging path: transforming it into a real pony model while still fully retaining surreal details, beautiful effects, and famous characters in the pony base. However, you can completely enhance its realism by using keywords related to realistic style and quality, as well as adding some opposite keywords in the negative prompt section. Additionally, try using natural language prompts combined with some NSFW keywords if you wish.

Update on June 8, 2024:
alpha 7 focuses on making image textures more realistic, which has resulted in some non-realistic pony details being reduced, along with the addition of tag_scores which are now mandatory

Update on June 3, 2024:

- Alpha 5: A lot of new data has been added, but I focused on fixing bugs and increasing stability first, so the model's realism has only improved slightly.

- Fixed Noise Spots: Resolved the common noise spots issue seen in pony models. This bug occurred when creating images with certain keywords or combinations of keywords that the pony model didn’t like. Yes, no more inexplicable noisy spots in the images.

- Reduced Dependence on tag_score: The influence of tag_score on image quality has been reduced to about 10%. Sometimes, it may even worsen the results.

- Still in Alpha: This is still an alpha version, so many issues still need to be addressed. Please let me know your feedback after trying this Alpha 5 version.

Updated May 27, 2024:

This is Alpha 1 version, also the first training version of the model, so there are many errors, not real enough, so don't wait too much. The reason for posting the Alpha version is to attract LOL interaction

Precedente
Sinfully Stylish (dramatic lighting) - v0.2 For SDXL
Successivo
Ev Ganin - Opus II

Dettagli del Modello

Tipo di modello

Checkpoint

Modello base

Pony

Versione del modello

v2.0

Hash del modello

40bf088344

Creatore

Discussione

Per favore log in per lasciare un commento.

Collezione di Modelli - DucHaiten-Pony-Real