详情
推荐
Based on FluxFusion
Based on DevMode
Based on Genova
Based on FluxUnchained
Fast & Low VRAM Flux.1D [4Gb tested, checkpoint]

Fast & Low VRAM Flux.1D [4Gb tested, checkpoint]

9.3K
50
21
#all in one
#基础模型
#fusion
#checkpoint
#low vram
#all-in-one
#FLUX
#flux fusion
#FLUX

This is a full checkpoint with 8-bit precision (FP8) based on Flux Fusion (which gives best results for me, and also there are variations with some other models). I made the checkpoint just for my own convenience. Unet, Clips and VAE merged to the checkpoint are described in this article.

It's okay to have 4GB VRAM and 32GB RAM to use the checkpoint. Simple testing ComfyUI workflow (.json file) is attached here as "Training Data" in .zip archive. 1024x1440 image generation takes ~80 seconds on my notebook with 4GB 3050 and i5-11400.

8 steps are enough to generate hi-res sharp images.

Just download and run it.

Enjoy.

查看译文

评分与评论

-- /5
0个评分

尚未收到足够的评分或评论

M
公告
2025-01-12
发布模型
2025-05-31
更新模型信息
模型详情
类型
Checkpoint
发布时间
2025-01-08
基础模型
Flux.1 D
版本介绍

Based on FluxFusion
Generally SFW

许可范围
来源: civitai

1. 转载模型仅供学习与交流分享,其版权及最终解释权归原作者。

2. 模型原作者如需认领模型,请通过官方渠道联系海艺AI工作人员进行认证。我们致力于保护每一位创作者的权益。 点击去认领

创作许可范围
在线生图
进行融合
允许下载
商业许可范围
生成图片可出售或用于商业目的
允许模型转售或融合后出售
QR Code
下载SeaArt App
在移动端继续你的AI创作之旅