models/Illustrious-XL SmoothFT - smoothFT-SPO

Illustrious-XL SmoothFT - smoothFT-SPO

|
10/17/2025
|
5:39:01 PM
| Discussion|
0
Lara Croft with braided ponytail reclining on a white couch indoors, wearing a white tank top and black yoga pants, with a relaxed and confident expression.

Recommended Prompts

1girl, solo, best quality

Recommended Negative Prompts

lowres, low quality, worst quality, bad anatomy, bad hands, signature, displeasing, watermark

Recommended Parameters

samplers

DPM2 a, Euler a

steps

28 - 48

cfg

6.5 - 10.5

clip skip

2

resolution

832x1216, 896x1216

vae

sdxlFP16.vae.safetensors

Recommended Hires (High-Resolution) Parameters

upscaler

4x_NMKD-YandereNeoXL_200k

upscale

1.5

steps

30

denoising strength

0.3 - 0.6

Tips

SPO version generally produces better compositions, details and anatomy than the normal version and is recommended.

The normal version stays truer to the original Illustrious model.

The fine-tune involved training on the same dataset as Bijutsubu - v1.0 and re-merging weights to retain characteristics while fixing block artifact issues.

Version Highlights

SPO version at strength 1.25

Illustrious-XL SmoothFT

UPDATE: Added SOLID version, a merge of SPO and NoobAI XL v-pred (the resulting model is normal) - it features richer solid colours and smoother gradients.

UPDATE: Added SPO version, thanks to qelt for the suggestion!

About SPO version: This version generally produces better compositions, details and anatomy than the normal version, so I recommend it. The normal version is most true to the original Illustrious model.


Smooth Fine-Tune of the Illustrious-XL base model

This is a personal fine-tune of Illustrious-XL - v0.1 | Stable Diffusion XL Checkpoint

It was trained for one epoch on the same dataset I used for Bijutsubu - v1.0

The fine-tune was then re-merged with the original model using the weights:

0.5,0.3,0.3,0.3,0.15,0.15,0.15,0.15,0.15,0.15,1,0,0,0,0.15,0.15,0.15,0.15,0.15,0.15

This was done to retain the characteristics of the original model, while helping fix the block artifact issues I ran into with Illustrious, which are exaggerated by image compression even further:

To illustrate (contrast has been enhanced):

Left: original; Right: SmoothFT

Another example:

The model obviously underwent other changes as a result of the FT, but largely remains true to the original base model.

Thank you to Angel and OnomaAI for this amazing model.

License

Contributor

Previous
Joseph Virtuoso - Style - IllustriousXL - Noob LoRa - v1.0
Next
Baroque Glitchcore - Flux

Model Details

Model type

Checkpoint

Base model

Illustrious

Model version

smoothFT-SPO

Model hash

ac1faa25f6

Creator

Discussion

Please log in to leave a comment.

Images by Illustrious-XL SmoothFT - smoothFT-SPO

anime Images

base model Images