So i started to get into this ai image generating stuff 3 months ago, and now this is my first Lora model. i made this using exclusively this site and since i have a 16 years old pc, i was unable to test the Lora by using other methods, so basically this is the testing phase...the batch images looked worth to try.
Photogenic_v1
LORA
Run1K
Version Detail
SD 1.5
2700
3
So my goal with this model was to bring out the facial details without having to use Adtailer. Since this didn't work out, i need to figure out things so i can train the modell further.
Although with ADtailer it works pretty good.
You can use the following settings to get my modell facial details on any style with any SD 1.5 modell.
You should add the lora under the model with 0.8 strength, and also under adtailer with 1.0 strength.
Sampling method: DPM++ SDE Karras
Steps: 20-25
cfg: 3-5
clip skip: 2
ADtailer settings
modell: face_yolov8n.pt
LORA: lora.TA_trained:1.0 (my lora strenght:1.0)
prompt: photogenic_LDG
threshold: 0.5-0.55 (depending how far is the character)
Inpaint mask blur: 4
Denoising Strength: 0.45-0.5 (depending on the face angle)
Project Permissions
Use in TENSOR GREEN Online
As a online training base model on TENSOR GREEN
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
![(masterpiece, best quality, photorealistic, high resolution, 8K raw photo, artstation) Half-body shot, Asian Girl, [Lisa Blackpink: Jisoo Blackpink:0.5], red eyes, elegant, thoughtful, reddish yellow lips, gothic, emo, dark, rock clothing, ((loose hair, black with white color)), good quality, cyberpunk, gothic
,Detailedface, photogenic_LDG](https://image.tensorartassets.com/cdn-cgi/image/anim=false,plain=false,w=300,q=85/posts/images/724745713946237461/bc02083b-1efe-44b0-bed3-a2b06db062f8)
Describe the image you want to generate, then press Enter to send.