Recommended Prompts
red lips,skindentation
((masterpiece)),((best quality)),(ultra-detailed),absurdres,extremely detailed CG unity 8k wallpaper,Official Art,Accurate describe shapes,beautiful face,expressive eyes,looking at viewer,solo,close-up,scenery,anime screencap,dramatic lighting,seductive smile,1girl,<lora:MatureFemaleSDXL-LoCon:1> (mature female,older,huge breasts:1.4),milf,motherly,wide hips,curvy,collarbone,lips,HDR
Recommended Negative Prompts
lowres,text,error,cropped,(worst quality,bad anatomy,low quality:1.4),bad hands,jpeg artifacts,signature,missing fingers,watermark,extra digit,username,fewer digits,blurry,artist name,side view,profile,b&w,weird colors,bad art,poorly drawn,disfigured,deformed,extra limbs,multiple views,zoom layer,projected inset,out of frame,face out of frames,hat,holding items,nsfw,nipples,younger,monochrome,interlocked fingers
| samplers | DPM++ 2M Karras, Euler a | |
| steps | 30 | |
| cfg | 7 | |
| clip skip | 2 | |
| resolution | 768×1152 | |
Tips
- Use red lips and skindentation prompts if the face does not look mature enough.
- Compare different Lora versions to find the best match for your project needs.
This is the first time I train concept Lora, comments are appriciate
Recommend Prompt: You can try red lips and skindentation if the face not look mature enough
The difference between 3 LoRA versions are training different methods and datasets. V1 is trained on Usual Dreambooth, PixAI is trained on PixAI’s New Lora Maker, SeaArt trained on their Lora Training. Mix is like its name, the mix of all three.
LoHA is trained with V1’s dataset, but with LoHA training method and it gave kinda different result. LoCon has an improvement of dataset from V1. And A1111 is now support for LyCORIS so you no longer need to install extensions to use LoHA version
You can try them at:
-
V1: https://tensor.art/models/630686144910323394?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
PixAI2Hassaku: https://pixai.art/model/1674859840667709249
-
SeaArt2: https://www.seaart.ai/models/detail/458de40c5f204ba39e66a6d7a487d50b
-
Mix: https://tensor.art/models/630686303824113993?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
Mix2: https://tensor.art/models/662661502119061140?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
Mix3: https://tensor.art/models/662685515281164293?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
LoHA: https://tensor.art/models/634359265366181071?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
LoCon: https://tensor.art/models/635857487397998595?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
LoCon2: https://tensor.art/models/669254659170407547?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
Tensor Exclusive Version: https://tensor.art/models/664141672403420166?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
SDXL: https://tensor.art/models/694129632280258249?source_id=nz-_pFzqlkO3rPsqbHvw9REl
-
Pony: https://tensor.art/models/741765466747509460?source_id=nz-_pFzqlkO3rPsqbHvw9REl
Since this Lora has too many versions, I think I would recommend you using 1 of 3 best versions: LoCon, Mix3 and LoCon2. The comparasion between them is at gallery.
The newest version is for SDXL, you can ignore it if you are using SD15
There are some images I left with no prompt, some are from PixAI and some are from tensor.art. You can download and you use “SD Prompt Reader” to read prompt
