modelle/TalmendoXL - SDXL Uncensored Full Model - v1.1-Beta

TalmendoXL - SDXL Uncensored Full Model - v1.1-Beta

|
10/16/2025
|
9:31:14 AM
| Discussion|
0
A surreal lighthouse towering over a dry riverbed with vibrant swirling colors and warped geometric forms in the background.
Korean model with long dark hair wearing a black dress with deep neckline, posing confidently in a professional red carpet photoshoot with makeup highlight.
Close-up of a female cyborg with a white mechanical face showing exposed wires and tubes, blending human and robotic elements in intricate detail.

Empfohlene Prompts

4k, highly detailed

Empfohlene Negative Prompts

graphite, crayon, soft, drawing, render cgi, impressionist, deformed, mutated, disfigured, distorted, blurry, sketch, grainy, (ugly:0.3), anime cartoon illustration, vignette, bokeh, child

Empfohlene Parameter

samplers

Heun, Euler, DPM++ 2M, DPM++ 2M SDE Karras

steps

30 - 40

cfg

6 - 10.5

clip skip

2

resolution

1024x1024, 896x1152, 832x1216, 768x1344, 1152x896, 1216x832, 1344x768, 1344x768, 768x1344, 896x1152, 1152x896

Empfohlene Hires (Hochauflösungs-) Parameter

denoising strength

0.25

Tipps

Use "natural light" for natural look

"full body shot" works quite well

Directions should also be easy to prompt for with "from the side/front/below"

Versions-Highlights

  • Hugely improved image quality, less grain

  • Less artifacts, like wrong limbs, bad hands

  • More variety body shapes

TalmendoXL - Uncensored SDXL

Beta v1.1

Attempt to uncensor SDXL and bias it more towards photorealism and non professional images.

Should be just as good at non nude images as SDXL, but they will be less professional looking and more like an amateur photo with more natural lighting. Might or might not be to your preference.

Tips: Use "natural light" for natural look, "full body shot" works quite well and directions should also be easy to prompt for with "from the side/front/below"

Recommended:

Sampler: Heun, Euler or DPM++ 2M

CFG: 6-10.5

Steps: 30

Resolution: 1024x1024, 896x1152, 832x1216, 768x1344 and their inverse (Same as SDXL Base)

Changelog

1.1

  • Much higher image quality, overall sharper images

  • More skin details

  • More different body types

Resources

Captioning done with: Talmendo/blip2-for-sd (github.com)

Mitwirkende

Zurück
Illustration Concept - Style V
Weiter
Wan Video 2.2 - ComfyUI Repack - 14B Image-to-Video

Modell-Details

Modelltyp

Checkpoint

Basismodell

SDXL 1.0

Modellversion

v1.1-Beta

Modell-Hash

7fb8947de2

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Bilder von TalmendoXL - SDXL Uncensored Full Model - v1.1-Beta

Bilder mit basismodell

Bilder mit weiblich

Bilder mit fotorealistisch

Bilder mit sexy