Download
2 variants available
Other Formats
This checkpoint includes a config file, download and place it along side the checkpoint.

730 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2210 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
AnimaThe Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Built on NVIDIA Cosmos
一份较为庞大的自动化工作流,共使用了19个插件,很多都是比较通用的插件,一些插件是纯python对环境没有影响,小部分插件也许会对您的环境产生影响,请酌情选择使用
该工作流即使是一位新手您也可以快速上手,参数都由面板控制能够快速,整体也更加直观简洁
有任何建议或使用上疑惑的您都可以私信或评论~看到都会进行回复(虽然我对comfyui的了解也不是很深就是了)
注:本人对danbooru-Gallery的参数控制面板 (Parameter Control Panel)节点的js文件做了修改,使其可以与tile模型进行联动以优化使用体验
关于js文件的路径:custom_nodes\ComfyUI-Danbooru-Gallery\js\parameter_control_panel
直接在comfyui启动器的首页点自定义节点后根据路径直接替换该路径下的js文件即可
小提示:您可以使用键盘的1/2/3来跳转到对应的节点组
关于版本:
v2.0
修改了整体架构,也同时修复了一些遗留bug,使其在使用上更加方便,页面也变得更加简洁
v1.3
修复了我个人在使用及测试时所遇到的各种问题,大概就是最终版了,请直接下载该版本
v1.2
修复了WD反推不起效的问题以及在参数页面增加了二次采样的步数与CFG值
v1.1
修复了提示词切换在一定情况下会导致D站画廊的附属节点不起效与一些遗留问题
关于工作流所包含的功能:Ciallo~ (∠・ω< )⌒★
更详细的说明(推荐配合工作流更好理解):https://mihama-onani-0721.netlify.app/
模型选择更加便捷,anima与SDXL模型可直接快速便捷的切换
支持anima与SDXL分别进行一采与二采/SD放大
常用参数与模型选择均收纳进可视化参数面板,选项更直观
支持anima与SDXL自动切换tile模型,不用每次都手动调整
支持 WD14 反推、Danbooru 取图、LLM API 润色提示词,半自动生成提示词
再说就太长了喵,总之捏~该工作流是一份面向新手到老手的自动化单人工作流
工作流较复杂,依赖较多自定义节点,首次使用请用 ComfyUI Manager 的"Install Missing Custom Nodes"一键安装或在下方插件列表按需求单独安装
—————————————————
插件列表 Plugin list:
1. rgthree-comfy
https://github.com/rgthree/rgthree-comfy
https://github.com/ltdrdata/ComfyUI-Impact-Pack
3. ComfyUI-Impact-Subpack
https://github.com/ltdrdata/ComfyUI-Impact-Subpack
4. WAS Node Suite
https://github.com/WASasquatch/was-node-suite-comfyui
5. ComfyUI-KJNodes
https://github.com/kijai/ComfyUI-KJNodes
6. ComfyUI-Custom-Scripts
https://github.com/pythongosssss/ComfyUI-Custom-Scripts
7. ComfyUI-WD14-Tagger
https://github.com/pythongosssss/ComfyUI-WD14-Tagger
8. ComfyUI-Easy-Use
https://github.com/yolain/ComfyUI-Easy-Use
9. comfyui controlnet aux
https://github.com/Fannovel16/comfyui_controlnet_aux
10. ComfyUI-Anima-LLLite
https://github.com/kohya-ss/ComfyUI-Anima-LLLite
11. ComfyUI-UltimateSDUpscale-FLS-LLLite
https://github.com/Lebensignal/ComfyUI-UltimateSDUpscale-FLS-LLLite
12. cg-image-filter
https://github.com/chrisgoringe/cg-image-filter
13. ComfyUI-ZML-Image
https://github.com/zml-w/ComfyUI-ZML-Image
14. ComfyUI-Danbooru-Gallery
https://github.com/Aaalice233/ComfyUI-Danbooru-Gallery
15.ComfyUI-Danbooru-Tag
https://github.com/RafealaSilva/ComfyUI-Danbooru-Tag-Sorter-Node
16.SafeTagDedup (喵喵喵~记得下载哦~)
https://github.com/mihama0721/ComfyUI_SafeTagDedup
17.ComfyUI-Prompt-Manager
https://github.com/FranckyB/ComfyUI-Prompt-Manager
18.advancedDynamicTextFilter
https://github.com/SararaYu/Comfyui-TAG_filter
19.comfyui_LLM_party
https://github.com/heshengtao/comfyui_LLM_party
—————————————————
推荐模型如下:
(面部/手部与反推模型可根据自身需求选择在设置好的控制面板处更换)
光辉CN控制(推荐深度与姿态 目前V2可以切换为其它)
Illustrious-XL pose: https://civitai.com/models/1359846/illustrious-xl-controlnet-openpose
Illustrious-XL Depthhttps://civitai.com/models/1023507/illustrious-xl-depth-midas
tile模型下载(可选)(不用tile模型的话请根据图片所示关闭tile模型)
(不用两个都下,根据你要用的模型选择就行)
anima Tile v2:https://civitai.red/models/2708551/anima-tile-and-repair-controlnet-lllite?modelVersionId=3068951
光辉 tile模型 Illustrious Tile model
Illustrious-XL Tile : https://civitai.com/models/1102581/illustrious-xl-tile
NOOB tile模型 NOOB Tile model
Eugeoter/noob-sdxl-controlnet-tile: https://huggingface.co/Eugeoter/noob-sdxl-controlnet-tile

