models/A-mix [Illustrious] - A - mix

A-mix [Illustrious] - A - mix

|
7/14/2025
|
5:19:07 AM
| Discussion

Recommended Prompts

1girl, solo, looking at viewer, masterpiece, detailed, best quality, high detail, depth of field, very aesthetic, 8k, dynamic pose, dynamic angle, adult, aged up

Recommended Negative Prompts

lowres, worst quality, low quality, bad anatomy, bad hands, jpeg artifacts, signature, watermark, text, logo, artist name, extra digits, censored, patreon username, loli

Recommended Parameters

samplers

Euler a, DPM++ 2M Karras

steps

20 - 50

cfg

5 - 7

resolution

768x1152, 768x1152

other models

hassakuwai_allust++ (291d5e0d1f)

Recommended Hires (High-Resolution) Parameters

upscaler

None

upscale

1.4 - 2

steps

10

denoising strength

0.1 - 0.2

Tips

Use text-to-image Highres fix, followed by image-to-image Face fix, then upscale x2 for better results.

Version Highlights

Positive and Negative prompt I'm using on ForgeUI

POS - masterwork, masterpiece, best quality, detailed, depth of field, , high detail, best quality, very aesthetic, 8k, dynamic pose, depth of field, dynamic angle, adult, aged up

NEG - lowres, worst quality, low quality, bad anatomy, bad hands, jpeg artifacts, signature, watermark, text, logo, artist name, extra digits, censored, patreon username

Base Model

A base model that (IMO) dose anime, 2.5 and realistic pretty well and should compatible with most Illustrious stuff. Have fun 😁

Settings for Civitai Generator

My POS and NEG prompt helps

CFG Scale - 5-7

Sampler - Euler a / DPM++ 2M Karras

Steps - 40-50

Denoise - 0.5

____

Process for a better result

Text-to-image Highres fix >>> Image-to-image Face fix >>> Upscale x2

HMU for if you have better settings

My settings for ForgeUI

Generation

Sampling method - Euler a

Schedule type - Automatic

Sampling steps - 20

Dimensions - 768 x 1152

CFG Scale - 6

Highres. fix

Upscaler - None (works for me)

Hires steps - 10

Denoising strength - 0.1

Upscale by - 1.5-2

Previous
Pony: People's Works v1-v6 - v4_noobEv1.0
Next
Anti-blur Flux Lora - v1.0

Model Details

Model type

Checkpoint

Base model

Illustrious

Model version

A - mix

Model hash

b199b92ee9

Trained words

pos: masterwork, masterpiece, best quality, detailed, depth of field, high detail, very aesthetic
neg: lowres, worst quality, low quality, bad anatomy, bad hands

Creator

Discussion

Please log in to leave a comment.