Empfohlene Prompts

photograph, Canon DSLR, rough digital painting, movie still, (full body:1.2), 1boy, man, handsome, solo, [:fantastical costume design, :0.2] warlord, chinese, pink hair, (solid:1) build, natural sunlight, interior, in a Palewave Amazonian tribal village<lora:EnvySendNoodzXL01:-2><lora:EnvyZoomSliderXL01:1.25>

Empfohlene Negative Prompts

nsfw, western comics, comics, painting, child, anime

Empfohlene Parameter

samplers

DPM++ 2M SDE Karras

steps

20

cfg

6.5

resolution

832x1248

vae

sdxl_vae.safetensors (235745af8d)

other models

!EnvyMegaMixXL01 (cf60f2c41c), juggernautXL_version6Rundiffusion (1fe6c7ec54)

Tipps

Use v1.0-negated if the generator does not allow negative zoom values to achieve zooming out effect.

The zoom value ranges approximately from -1.25 to +1.25, but results can vary based on the subject and checkpoint used.

Model was trained focusing on human subjects and is suitable for both anime and photorealistic styles.

It has not been tested with animals or scenery, so results may vary (YMMV).

Civit's generator not letting you use a negative value? Use v1.0-negated, which makes it so positive values zoom out!

Zooms in and out on character portraits. I've tried to balance it so that 1.0 is zoomed in close to the character's face, and -1.0 is a full body shot, however, your results may vary depending on your subject and what checkpoint you're using. I've had generally good luck up to +/-1.25 and even more in some cases.

This works with both anime and photorealistic generations. It was trained with humans in mind, and has not been tested with animals or scenery, so YMMV.

Mitwirkende

Zurück
Neurocore Anime Shadow Circuit by ChronoKight - [FLUX & IL] - ILLUSTRIOUS
Weiter
Phlux - Photorealism with style (incredible texture and lighting) - Phlux_V1

Modell-Details

Modelltyp

LORA

Basismodell

SDXL 1.0

Modellversion

v1.0

Modell-Hash

7b02667022

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.