モデル/epi_noiseoffset - v2

epi_noiseoffset - v2

|
7/24/2025
|
11:30:46 AM
| Discussion

推奨プロンプト

dark studio,rim lighting,two tone lighting,dimly lit,low key

sharp focus

推奨ネガティブプロンプト

lowres, cropped, duplicate, text, morbid, error, mutilated, out of frame, worst quality, low quality, jpeg artifacts, extra fingers, deformed, mutated hands, poorly drawn hands, bad anatomy, poorly drawn face, mutation, blurry, cloned face, extra limbs, disfigured, bad proportions, malformed limbs, gross proportions, extra arms, missing arms, extra legs, username, missing legs, watermark, fused fingers, signature, too many fingers, long neck

推奨パラメータ

samplers

DDIM, DPM++ 2M Karras

steps

28 - 30

cfg

5 - 7

resolution

512x768

other models

epi_hyperphotogodess (a89f142591)

推奨ハイレゾパラメータ

upscaler

4x_NMKD-Superscale-SP_178000_G

upscale

2

denoising strength

0.5

ヒント

Weighting depends often on Sampler, kept it in the low-middle range.

Custom weighting is needed sometimes.

Works better if you use good keywords like dark studio, rim lighting, two tone lighting, dimly lit, low key.

バージョンのハイライト

bigger and a bit better

UPDATE: v2-pynoise released, read the Version changes/notes

LORA based on the Noise Offset post for better contrast and darker images.

Weighting depends often on Sampler, kept it in the low-middle range (Maybe i will put up a stronger one).

Custom weighting is needed sometimes.

Works better if u use good keywords like: dark studio, rim lighting, two tone lighting, dimly lit, low key etc.

Didn't like the color saturation and image compositions from the theovercomer8sContrastFix_sd15 so i made this one.

UPDATE: v2 is slightly stronger in the whole composition

Update 2: added safetensor file

Quick Comparsion

投稿者

前の画像
Flatline - Illus x Niji [BETA] - v1.0
次の画像
All Disney Princess XL LoRA Model from Ralph Breaks the Internet - v2.0

モデル詳細

モデルタイプ

LORA

ベースモデル

SD 1.5

モデルバージョン

v2

モデルハッシュ

81680c064e

作成者

ディスカッション

コメントを残すには log in してください。

モデルコレクション - epi_noiseoffset