Your current browser has compatibility issues. Please switch toChrome for uninterrupted access.

DHXL_v1.0

711
15
4
10
Commercial UseCGI styleGirl
Recently Updated: 25/04/10First Published: 25/02/28
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info
CGI style,Girl,Checkpoint,SDXLImage info

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

Patreon is here (but there's nothing in it):
https://linktr.ee/Duc_Haiten

I created my Discord server. I'm still quite new to Discord server management, feel free to share your opinions.
https://discord.gg/vKEW6jqa49

After half a year, I finally completed my base model, DHXL. I can say that I was the only one who put a huge amount of time, money, and effort into it. DucHaitenXL is trained from IL 0.1, meaning it's based on the SDXL architecture but with a higher image resolution (1250x1250 at 1:1). DHXL was trained on a massive dataset. From my previous experience training PONY models, I separated different styles into 49 distinct keywords, from style_0 to style_48. However, unlike PONY, these are not quality-based keywords like scores; they are just priority markers for a particular art style. You don't have to use them if you don't find them necessary. I might later write a detailed guide explaining the specific effects of each keyword, but that will be in a separate post. With 49 style activation keywords, they can be used individually or combined to create unique new styles. However, it’s best to combine only up to six styles—any more, and stability decreases.

Example:
"style_12, style_9, style_22, style_8, style_24, style_37, BREAK"

Some might ask, "How is this different from LoRA?" The difference is that LoRA cannot be used with too many at once. It forces the checkpoint to follow its structure, while this method works as a mutual compromise, allowing for a shared understanding between the base model and the user-defined styles.

Recommended Settings:

DPM++ 2M
SGM Uniform
50 steps
CFG 8.5

2D-2.5D Negative Prompts:

(worst quality:1.5), (low quality:1.5), bad anatomy, bad or heavily deformed hands and fingers, extra limbs, missing limbs, conjoined fingers, signature, username, artist name

3D-Realistic Negative Prompts:

(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrows, cropped, extra limb, missing limbs, deformed hands, long neck, long body, signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist

Expand All

Discussion2

Most popular
|
Newest
Send
avatar
cigi cigi
amazing!
2025/03/24 19:35:57
0Reply
avatar
ChugAx
bổ!!!!!
2025/03/06 08:34:23
0Reply
No more comments
Favorite
Download
(6.46GB)
Verified:2025/02/28
safetensors
Version Details
Type
Checkpoint
Generation Count
711
Downloads
15
Base Model
SDXL
Recommended Parameters
Sampler method
DPM++ 2M, DPM++ 2S a, Euler a
CFG
8.5
VAE
None
License
Can be generated online
Can be merged
Commercial LicenseCommercial Use Rules
Generated images can be used for commercial purposes
Models can be resold or sold as merged models
*Licensing scope is set by the creator, users must use as per requirement and standards

Gallery4

Most popular
|
Newest
avatar
BTSPhoto
Image info
avatar
BTSPhoto
Image info
avatar
BTSPhoto
Image info
avatar
BTSPhoto
Image info