Diffus
Loslegen
modelle/DevlishPhotoRealism SDXL - SDXL 1.4

DevlishPhotoRealism SDXL - SDXL 1.4

Kate Thompson
|
10/23/2023
|
12:24:46 PM
| Discussion|
0

Verwandte Schlüsselwörter & Tags

basismodell,checkpoint,fotorealistisch,real,realism,sdxl 1.0
A surreal portrait featuring a woman's face merged with beluga whale-like smooth white textures, surrounded by floating, porous geometric shapes creating a warped, gravity-defying environment.
A slightly longer description of a futuristic woman in an orange and white space suit, generated using stable diffusion.
Close-up of a samurai in traditional black and gold armor, generated using Stable Diffusion AI.
AI generated image using stable diffusion of a Native American warrior wearing a traditional headdress adorned with feathers, detailed face paint, and colorful beads.
A close-up portrait of a man with a thick beard, wearing a turban and desert attire, generated using Stable Diffusion.
An AI generated image using stable diffusion featuring an elderly man with white hair and glasses, smiling and holding a Marvel comic book in New York City. The scene is set at night with the glowing Empire State Building, a full moon, and the northern lights in the background.
A close-up portrait of a smiling woman with short red hair, captured against a soft background using AI generated image with Stable Diffusion.
A colorful portrait of a tiger created in an abstract art style using Stable Diffusion.
An AI generated image using stable diffusion depicts an imposing alien warrior with an ornate helmet and glowing eyes, set against a desert landscape with ancient ruins.
A medieval knight in full metallic armor with intricate designs, standing in a stone archway. This is an AI generated image using stable diffusion.
Realistic portrait of an elderly man with an intense gaze and blue eyes, wearing a hat, AI generated using stable diffusion
A close-up portrait of a soldier with an intense expression on his face and a battle-worn helmet, generated using AI-driven Stable Diffusion.

Empfohlene Parameter

samplers

DPM++ 2M Karras, Euler a, DPM++ SDE Karras, DPM++ 3M SDE Karras

steps

20 - 80

cfg

3 - 7

resolution

1024x640, 960x640, 1024x768, 640x1024, 1536x1024, 768x1024

other models

SDXL_DevlishPhotoRealism_v1.5 (9be563ddce)

Empfohlene Hires (Hochauflösungs-) Parameter

upscaler

4x_NMKD-Superscale-SP_178000_G, 8x_NMKD-Superscale_150000_G

upscale

1.5 - 2

steps

20 - 80

denoising strength

0.2 - 0.5

Tipps

You should set 'CFG Scale' to something around 4-5 for the most realistic results.

My first attempt to create a photorealistic SDXL-Model.
I hope, you like it.
I merged it on base of the default SD-XL model with several different models. (Around 40 merges)
SD-XL VAE is embedded.
I strongly recommend ADetailer.

You should set "CFG Scale" to something around 4-5 to get the most realistic results.

v1.2 is an updated version with some added elements with a slight tendency to be a miss of the dark. 😊

v1.3 has new improved details, better nsfw results, I also refined the output for better photo realism, the missus is still here 😉

v1.4 has better results for NSFW images, I also refined some details, less missus but improvements in base model 😊

v1.5 is better fine tuned, improved details, refined output

v1.6 is an improved model with better details and better NSFW compatibility.


A music video, I made using this model and Udio and wav2.lip and KlingAi and much more is here:


Zurück
Better than words - v2.0
Weiter
fennfoto - ff1
Dieses Modell verwenden

Modell-Details

Modelltyp

Checkpoint

Basismodell

SDXL 1.0

Modellversion

SDXL 1.4

Modell-Hash

9be563ddce

Ersteller

Devilmarkus's avatar
Devilmarkus

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Bilder von DevlishPhotoRealism SDXL - SDXL 1.4

Bilder mit basismodell

Bilder mit fotorealistisch

Bilder mit realism