Haru_puding

CHECKPOINT
Original


Updated:

542

It's a model that can pick cute characters.

It may be unstable because it is an early version, but we have confirmed that it is fine in most situations.

This is the recommended setting for the model.

CFG scale 3~7 (Personally 5 was the best.)

Step and Sampler

DPM++ SDE karras 16~40

DPM++ 2M karras 16~30

Euler a 30~

CLIP skip 2~3

The negative prompts of the examples are as follows.

(low quality, worst quality:1.4), extra fingers, fewer fingers, (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2), EasynegativeV2, negative_hand-neg, bad-artist-anime, bad-hands-5, nipple, pussy, covered nipples, Cameltoe, blurry, (pencil)

かわいいキャラクターを選べるモデルです。

初期バージョンなので不安定かもしれませんが、ほとんどの状況では元気であることを確認しました。

モデルの推奨セッティングです。

CFG scale 3〜7 (個人的には5が一番良かったです。)

StepとSampler

DPM++ SDE karras 16〜40

DPM++ 2M karras 16~30

Euler a 30~

CLIP skip 2~3

例の否定プロムポートは下記の通りです。

(low quality, worst quality:1.4), extra fingers, fewer fingers, (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2), EasynegativeV2, negative_hand-neg, bad-artist-anime, bad-hands-5, nipple, pussy, covered nipples, Cameltoe, blurry, (pencil)

Version Detail

SD 1.5
1
1
This model adds new learning materials and outputs deliverables that feel different from the existing V1 model. Compared to the conventional model, the overall feeling of the picture has changed, and the versatility has been greatly improved. このモデルは、新しい学習資料を追加して、既存のV1モデルとは違う感じの成果物を出力します。 従来のモデルに比べて絵の全般的な感じが変わり、汎用性が大幅に改善されました。

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR GREEN Online

  • As a online training base model on TENSOR GREEN

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.