qwen image 2.1的去和谐clip模型..
应用场景:https://civarchive.com/models/2957332/qwen-image-21-fix-v10
主要针对使用Clip模型接"Generate Text"来增强提示词,如果用原本的clip它会不给你生成NSFW内容.(说实话我当时看到那个工作流才知道这个clip模型能生成文本..)
我没有研究过这个东西的详细流程,但是鉴于这个东西可能非常小众所以就搞了..
流程是先用16bf的模型走https://github.com/p-e-w/heretic去和谐,
然后使用https://github.com/silveroxides/convert_to_quant进行量化.
它的大小不知道为什么比原本的int8_covrot格式大了2GB,
但是测试下来功能是达到预期的.(但是应该还是专门做PE的模型或者用LLM更好)
在上传的期间去试了一下专用的PE模型.是史啊,太慢了... 还是外接人工智能,或者智能人工更好..
注意,这个不是PE模型.. 就是垫吧垫吧能用的水平,绘制和提示词增强用同一个clip能省点显存而已. 别指望它生成多好的提示词.
Description
FAQ
Comments (1)
跟 https://civitai.red/models/2955374/ 是不是没什么区别
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.