多concept人物训练教程https://www.bilibili.com/read/cv22050074
Description
如果您想给给史尔特尔换衣服,请使用这个版本.这个版本训练集中只放了大头
If you want to change clothes for Surtr, please use this version. This version only puts the portraits in the training set
FAQ
Comments (27)
好精致的模组，同是一样的模型为什么大大的画面如此优秀，好羡慕嫉妒恨。是要加载什么VAE文件吗
大佬，请问有q群吗或者教程，这效果太tm牛逼了，想学
大佬想问一下，为什么我的lora无法载入呢？提示是Error running process: /content/stable-diffusion-webui/extensions/sd-webui-additional-networks/scripts/additional_networks.py，用的是abyssorange的model
找到原因了，我的webui版本太旧了，换新的就能用了
这用的是哪个模型啊？大佬
你可以保存一张大佬的图片用你的webui的PNGinfo这个功能来查看的,我查出来的是e4b17ce185这个哈希,可以搜出来,但是感觉示例图片画风实在差得有点多
不对,搜不到
估计是什么私人模型吧....唉
欸???好像是anything-v4.5-pruned啊??
但是吧,我用自己的跑出来差很多啊
呜呜呜
parameters
1girl,coralcoast,sitting
Negative prompt: sketch, duplicate, ugly, huge eyes, text, logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), crown braid, ((2girl)), (deformed fingers:1.2), (long fingers:1.2),succubus wings,horn,succubus horn,succubus hairstyle, (bad-artist-anime), bad-artist, bad hand,
Steps: 21, Sampler: DPM++ 2M Karras, CFG scale: 7.5, Seed: 2234044241, Size: 448x704, Model hash: e4b17ce185, Denoising strength: 0.51, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: surtr3(fe6ab3841b52), AddNet Weight A 1: 1, AddNet Weight B 1: 1, Hires upscale: 2, Hires steps: 20, Hires upscaler: Latent
这是第一张的
啊我靠是第二张的啊
@610 对
a4.5
@zbw 大佬,我是真的找不到你说的那个vae,能不能劳驾你给个链接啥的啊
@zbw辛苦了,谢谢啊
@610 sd1.4vae,用sd1.5vae差不多
@zbw 哦哦,谢谢谢谢,辛苦了辛苦了
Please Kal'tsit and Amiya !!
recommended lora weight?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.