Model Information

LeMix T9 - Image 1
LeMix T9 - Image 2
LeMix T9 - Image 3
LeMix T9 - Image 4
LeMix T9 - Image 5
LeMix T9 - Image 6

Description

This is a well-validated comprehensive foundation model that can serve as a training starting point and can be directly applied to real-world applications. Its strong compatibility with LoRA makes it highly flexible and adaptable.

ā˜… Please upload at least one photo made using the LeMix Realistic Asians model uploaded to CIVITAI to the gallery.

Recommended generation parameter
Sampling method & type: DPM++ 2M Karras
Sampling steps: 28 ~ 50
CFG Scale: 7
Clip: 1
Resolution: 512x768, 576x864
Negative prompts: ng_deepnegative_v1_75t,((badhandv4)),(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,poorly drawn face,bad legs,bad arms,bad hands,bad anatomy,missing limb,extra limb

To achieve more realistic character details, it is recommended to use Adetailer (install via Github) with the following parameters:

  • Face model: face_yolov8n

  • For close-up portraits: redraw amplitude at 0.25-0.3

  • For upper body portraits: redraw amplitude at 0.3-0.35

  • For full body portraits: redraw amplitude at 0.35-0.4

If you like my model, you can encourage me with "buzz".

I only publish my models on "Civitai", the rest are all stolen.

LeMix T9

T9 Full

241downloads
Download Model

Model Details

Type
AI Model
Task
text-to-image
Subtype
Safetensors / Checkpoint AI Model
Created
Updated
June 7, 2026

Related Models