home models images videos 3D Models articles comics bounties challenges updates shop

Animated models of General mix

Name: Animated models of General mix
Rating: 5 (273 reviews)
Author: Red_Moon_AI

273

2.3k

Updated: Oct 5, 2024

base model

Download

1 variant available

fp16 SafeTensor

bw-merge-meinahentai_v4-bw-merge-veela_v11-fsV12_v10-0-0-half.safetensors

Half precision, best balance • 1.99 GB

Verified: 3 years ago

Download (1.99 GB)

Details

Type

Checkpoint Merge

Stats

358

Reviews

Very Positive

(77)

Published

Jul 1, 2023

Base Model

SD 1.5

Hash

AutoV2

E667594B3B

Trigger Words

3D modeling

photos

real world

Tensors

About this version

It is a combination of heitai4+veela11+fsV12, using updated materials compared to the 0.4 version.

By adjusting the tags, you can generate both 2D and 2.5D styles. To generate a 2.5D image, three trigger words need to be used simultaneously, while no trigger words are required for the default 2D animation style.

It is not recommended to generate images with an aspect ratio exceeding 16:9 or 9:16, as it may result in severe distortion.

It is recommended to use Anything VAE and DPM++ 2M SDE Karras Sampling method for image generation.

The resolution should not exceed 768px.

It is advisable to add Bad hands-5 to reduce the probability of bad results. Avoid using any magnification plugins.

Typically, img2img using R-ESRGAN 4x+ Anime6B can provide better results than Hires. fix.

Link to the model used for synthesis:

https://civitai.com/models/12606/meinahentai
https://civitai.com/models/68025/veela
https://civitai.com/models/91864/fs-v12

default creator card background decoration

1.1K

Red_Moon_AI

Joined Feb 7, 2023

License:

CreativeML Open RAIL-M Addendum

The version 0.4 is a merge of heitai3+veela10+fsV12.

Version 1.0 is a combination of heitai4+veela11+fsV12.

By adjusting the tag, 2D and 2.5D styles can be produced. Simultaneous use of three triggering words is necessary for creating a 2.5D image, whilst no triggering words are required for the default 2D animation output.

Creating images exceeding an aspect ratio of 16:9 or 9:16 is discouraged due to the potential for serious distortion.

We recommend the use of Anything VAE and DPM++ 2M SDE Karras Sampling method for image generation.

Resolutions over 768px should be avoided.

Adding 'Bad hands' is recommended to reduce the likelihood of undesirable outcomes. The use of any magnifying plugins for enlargement is not recommended.

Typically, utilizing 'img2img' with 'R-ESRGAN 4x+ Anime6B' provides this model with performance surpassing that of 'Hires. fix'.

Link to the model used for synthesis:

https://civitai.com/models/12606/meinahentai
https://civitai.com/models/68025/veela
https://civitai.com/models/91864/fs-v12