models/DucHaitenPonyReal - ponyrealbeta8

DucHaitenPonyReal - ponyrealbeta8

|
7/1/2024
|
8:15:53 AM
| Discussion
A dramatic water portrait at ocean sunset, created using Stable Diffusion AI. The left side shows a man with wet hair in splashing water, while the right side depicts a sunset over a water body with floating buoys.
A woman with rainbow hair in a red dress stands on a cliffside overlooking a river and lush greenery, AI generated with stable diffusion.
AI generated image using Stable Diffusion of a skeleton mage with glowing green eyes, wearing a detailed green robe with flaming patterns and holding a fiery staff.
An AI generated image using stable diffusion of a fiery woman with glowing embers and flames integrated into her body standing in a volcanic landscape.
A white nine-tailed fox with blue-tipped tails, created using AI image generation with Stable Diffusion.
Futuristic lighting fixtures along a forest pathway during dusk, an AI generated image using stable diffusion.
A fantasy warrior with glowing fiery skin intertwined with a fire dragon, created using AI and Stable Diffusion.
A majestic, AI-generated underwater dragon navigating through a vibrant, coral-rich seascape, created using Stable Diffusion.
A misty landscape with a solitary figure standing between ancient, abandoned structures, AI generated using Stable Diffusion
A cute cat with wide, glistening eyes sitting inside a honey jar, covered in dripping honey. AI generated image using Stable Diffusion.
A dark fantasy skeleton mage with glowing green eyes and a red magic staff created using Stable Diffusion.
AI generated image of a haunted graveyard with a gothic church in the background, created using stable diffusion. The scene is set at nighttime with eerie fog and tombstones.

Recommended Prompts

realistic style,quality,vivid colors,gold cinematic depth,natural language

score_9,score_8_up,score_7_up

Recommended Negative Prompts

noise spots,non-realistic pony details,tag_score

score_6,score_5,score_4,source_pony,(worst quality:1.2),(low quality:1.2),(normal quality:1.2),lowres,bad anatomy,bad hands,signature,watermarks,ugly,imperfect eyes,skewed eyes,unnatural face,unnatural body,error,extra limb,missing limbs,painting by bad-artist

Recommended Parameters

samplers

DPM++ 2M

steps

30

cfg

8

clip skip

2

resolution

768x1128

other models

pony-real-beta-8 (9405535520)

Recommended Hires (High-Resolution) Parameters

upscaler

4x-UltraSharp

upscale

2

denoising strength

0.4

Tips

Enhance realism by using keywords related to realistic style and quality.

Add opposite keywords in the negative prompt section to balance the output.

Use natural language prompts combined with NSFW keywords for specific results.

Creator Sponsors

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

https://discord.gg/FPhQvFsqe2

If you like my content, support me at:

http://paypal.me/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.

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

Previous
CyberRealistic - v50Inpainting
Next
DucHaitenPonyReal - Beta4

Model Details

Model type

Checkpoint

Base model

Pony

Model version

pony-real-beta-8

Model hash

9405535520

Creator

Discussion

Please log in to leave a comment.

Images by DucHaitenPonyReal - ponyrealbeta8

A dramatic water portrait at ocean sunset, created using Stable Diffusion AI. The left side shows a man with wet hair in splashing water, while the right side depicts a sunset over a water body with floating buoys.
A woman with rainbow hair in a red dress stands on a cliffside overlooking a river and lush greenery, AI generated with stable diffusion.
AI generated image using Stable Diffusion of a skeleton mage with glowing green eyes, wearing a detailed green robe with flaming patterns and holding a fiery staff.
An AI generated image using stable diffusion of a fiery woman with glowing embers and flames integrated into her body standing in a volcanic landscape.
A white nine-tailed fox with blue-tipped tails, created using AI image generation with Stable Diffusion.
Futuristic lighting fixtures along a forest pathway during dusk, an AI generated image using stable diffusion.
A fantasy warrior with glowing fiery skin intertwined with a fire dragon, created using AI and Stable Diffusion.
A majestic, AI-generated underwater dragon navigating through a vibrant, coral-rich seascape, created using Stable Diffusion.
A misty landscape with a solitary figure standing between ancient, abandoned structures, AI generated using Stable Diffusion
A cute cat with wide, glistening eyes sitting inside a honey jar, covered in dripping honey. AI generated image using Stable Diffusion.
A dark fantasy skeleton mage with glowing green eyes and a red magic staff created using Stable Diffusion.
AI generated image of a haunted graveyard with a gothic church in the background, created using stable diffusion. The scene is set at nighttime with eerie fog and tombstones.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

photorealistic Images

Close-up portrait of a handsome athletic man with wet tousled black hair, subtle stubble, wearing a black leather jacket and white shirt, illuminated with dramatic cinematic lighting against a blurred urban night background with neon reflections.
Empty city street at night with reflections of lights on wet pavement, tall skyscrapers lining both sides.
Photorealistic portrait of a young blonde woman with heterochromia wearing an off-shoulder black shirt, standing against a peeling textured concrete wall under dramatic noir lighting casting shutter-like shadows.
Photorealistic young woman dressed as a nun in a black nun dress with cleavage, standing in a sunny garden with greenery and flowers.
Intricate ornamental design of a playing card featuring a geometric humanoid figure with sacred geometry patterns, metallic textures, and sharp angles in hyperrealistic digital art style.
Close-up of a supermodel wearing a metallic outfit with golden barbed-wire covering her eyes and plasma-like glowing fangs, sitting on a golden throne with vibrant magic bokeh effects.
Photorealistic scene of an astronaut sitting on a rocky mountain peak on Mars with a vast mountainous landscape, clouds, a large moon, starry cosmic sky, and an alien spaceship flying overhead.
A towering space elevator rises from a vibrant futuristic coastal city at twilight, with illuminated buildings and floating vehicles under dramatic cloud-lit skies.
Photorealistic image of a young man with wet medium-length black hair standing shirtless under a soaked dark blue trench coat on a rainy neon-lit city street at night, featuring cinematic lighting and a melancholic expression.
Close-up digital illustration of a woman with striking blue eyes, pink wavy hair, freckles, and glossy red lips, showcasing realistic skin textures and metallic makeup highlights.

sexy Images

A photo realistic painting of a gigantic prehistoric skeleton lying in a desert at sunset with a woman standing between its ribs, casting long shadows under dramatic, warm light.
A humanoid robot with cat ears and white mechanical armor sits crouched in a futuristic cockpit surrounded by advanced control panels and cables, with glowing orange eyes and a sleek black mask.
Anime-style young woman dressed in tactical gear and a worn headscarf standing against a stark desert background with rocky formations under a clear sky.
Portrait of a cyberpunk girl with pink hair, yellow eyes, sharp golden teeth, wearing a futuristic black outfit and metallic collar against a vibrant neon background.
Surreal sculptural artwork with twisted branches and human-like forms, split between a dark blue and vibrant yellow background
Watercolor painting of a punk girl with short pink hair wearing a black skull print crop top, red plaid skirt, ripped black tights, and black boots, showing a defiant pose with middle finger raised.
A girl with flowing ginger hair and green eyes kneeling outdoors wearing a tweed blazer, white shirt, black tie, and red Scottish kilt with wind lifting her hair and clothes, set against a cloudy sky and green mountainous landscape.
A striking portrait of a blonde woman wearing large neon orange glasses with vivid blue and red lighting on her face and hair, dressed in black against a white background.
A chubby woman wearing a multi-layered white bouffant dress with white stockings and black shoes, depicted in pastel watercolor style with delicate pencil lines and vibrant, smooth color transitions.
A night elf skeleton deathknight with long dark green hair and black eyes stands in a graveyard clutching a giant sword with green glowing runes, surrounded by tombstones and a gloomy sky.