Dream Teudoongie

Name: Dream Teudoongie
Rating: 5 (37 reviews)
Author: artificialecchi

242

Updated: Oct 4, 2024

celebrity

dreamlikeart kpop twice

Download (1.99 GB)

Verified: 2 years ago

PickleTensor

This asset is only available as a PickleTensor which is a deprecated and insecure format. We caution against using this asset until it can be converted to the modern SafeTensor format.

Details

Type	Checkpoint Trained
Stats	242 0
Reviews	Positive (41)
Published	Jan 28, 2023
Base Model	SD 1.5
Trigger Words	nabongs jeongie hiraimomo minatozaki sana godjihyo myouimina dubu chaengie choutzuyu
Hash	AutoV2 4C97B6A446

1 File

default creator card background decoration

artificialecchi

License:

CreativeML Open RAIL-M Addendum

This resource is intended to reproduce the likeness of a real person. Out of respect for this individual and in accordance with our Content Rules, only work-safe images and non-commercial use is permitted.

If you are this person or a legal representative of this person, and would like to request the removal of this resource, you can do so here.

Model dedicated to my fav kpop gg TWICE trained based on dreamlike-diffusion v1.0 model.

Suggested prompt format for best results (remove [ ] when actually prompting):

[trigger word], [describe place, clothes, action, etc], beautiful, gorgeous big anime eyes, illustration, realism, highly detailed, dreamlikeart, [artist 1], [artist 2], [artist 3]

Artists are optional but I suggest artist 1 as Jeremy Geddes and artist 2 is Warren Louw. Artist 3 can be random for variety. The first 2 artist sets a better base. Please feel free to experiment and share your outcome.

Suggested negative prompts (just copy paste this and adjust where necessary - for some reason it improves the output quality rather than actually doing all those negatives lol):

low-res, ugly, bad anatomy, extra limbs, missing limbs, grotesque, malformed, deformed, asymmetrical eyes, text, words, signature, watermark

Suggested samplers are Euler, Euler A, and DDIM. I personally LOVE DDIM.

Steps between 30-50 should be good.

CFG between 7 to 12 is good.

Best resolution is similar to dreamlike-diffusion:

512 x 768 (2:3)

768 x 512 (3:2)

640 x 640 (1:1)

As usual, feel free to experiment and share your results here.

Thank you for your time and interest.