[Community] LoRA extract版本LORA1024CD1024perfectWorld_v2Baked (ID: 31470)

[Community] LoRA extract版本LORA1024CD1024perfectWorld_v2Baked (ID: 31470)

LoRA extractions is not as good as the full model but it creates a compromise between size and quality and it can be used along other LoRA model with a full model. Credit goes the creator of the checkpoint in version description

Sorry, i do not accept anymore request link(s) in my comments "Suggestions for a model extraction?"

04.0417.23 Name version is limited to 10 25 character, make it impossible to see full name... see below "List of all LoRA model".

How to use it in AUTOMATIC1111 WebUI?

  • Place the LoRA model in .\stable-diffusion-webui\models\Lora then use <lora:filename:multiplier> in the prompt.

About the comparison:

  • Picture order: First = LoRA, Second = Fine-tuned Model, Third = Base Model

  • DM = Network Dimension ( 120=lower quality/low size, 320=higher quality/higher size ) same for CD = Conv Dimension (Rank)
    [CD is optionally if you wish to use it, install the extension: https://github.com/KohakuBlueleaf/a1111-sd-webui-locon (How? Extensions -> Install from URL)]
    Obviously Version "1024CV1024" or in short "1024" use more VRAM
    I did a large comparison DM+CV here

  • sample pictures does not use vea and LoRA model with SDv1.4

  • every model from (Stable Diffusion Base Model: mostly sd-v1-4.ckpt, model base is determined by highest % affinity) was extracted using Kohya_ss (Save precision: fp16)

  • Name format: <Type><DM> <CV><Name>

List of all LoRA model:

描述:

base: perfectWorld_v2Baked

This show that greater DM and CM are not exponential or linear better in term of quality improvement while file size is.

  1. First preview picture use DM 1024 + CD 1024 (best possible LoRA extraction but 1.9GB...).

  2. Second preview picture use only DM 1024 (CD 1024 is ignore as i did not install the locon extensions, more about CD in description).

  3. 04.02.22 - added DM-CV comparison extraction + all lora of the comparison in "Training Images"

训练词语:

名称: CompareLoRA_DM-CV.zip

大小 (KB): 25409624

类型: Training Data

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

名称: LORA1024CD1024perfectWorld_v2Baked.safetensors

大小 (KB): 2002602

类型: Model

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

[Community] LoRA extract

[Community] LoRA extract

[Community] LoRA extract

资源下载
下载价格VIP专享
仅限VIP下载升级VIP
犹豫不决让我们错失一次又一次机会!!!
原文链接:https://1111down.com/901033.html,转载请注明出处
由于网站升级,部分用户密码全部设置为111111,登入后自己修改, 并且VIP等级提升一级(包月提升至包季,包季提升到包年 包年提升至永久)
没有账号?注册  忘记密码?

社交账号快速登录