Workflow for Anima
Any feedback would be appreciated.
Downloads
Anima HF repo: https://huggingface.co/circlestone-labs/Anima
Anima civitai model page: https://civarchive.com/models/2458426/anima-official
Detectors (YOLO/SEG):
Hands (hand_yolov9c): https://huggingface.co/Bingsu/adetailer/blob/main/hand_yolov9c.pt
Face (face_yolov9c): https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt
Eye (Eyeful_v2-Paired or Eyeful_v2-Individual): https://civarchive.com/models/178518/eyeful-or-robust-eye-detection-for-adetailer-comfyui
NSFW (ntd11_anime_nsfw_segm_v5-variant1): https://civarchive.com/models/1313556/anime-nsfw-detectionadetailer-all-in-one
ControlNets LLite:
https://huggingface.co/kohya-ss/Anima-LLLite/tree/main
Tag order
[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]
Generation Settings
30-50 Steps
4-5 CFG
1MP Resolution e.g. 1024x1024 or 896x1152
er_sde, euler_a or dpmpp_2m_sde_gpu
Key Features:
LoRA
Detailers
Upscaling
Wildcards
ControlNet
Inpaint
Workflows included:
🟥Anima: Standard workflow version
🟨AnimaStandard: more simplistic version of the workflow
🟩AnimaBasic: more simplistic version of the standard workflow that lacks some of the advanced features for metadata and such
Custom Nodes
ComfyUI-Manager (by Comfy-Org)
https://github.com/Comfy-Org/ComfyUI-ManagerComfyUI-Impact-Pack (by ltdrdata)
https://github.com/ltdrdata/ComfyUI-Impact-PackComfyUI-Impact-Subpack (by ltdrdata)
https://github.com/ltdrdata/ComfyUI-Impact-Subpackrgthree-comfy (by rgthree)
https://github.com/rgthree/rgthree-comfyComfyUI-Image-Saver (by alexopus)
https://github.com/alexopus/ComfyUI-Image-SaverComfyUI-KJNodes (by kijai)
https://github.com/kijai/ComfyUI-KJNodesComfyUI-Lora-Manager (by willmiao)
https://github.com/willmiao/ComfyUI-Lora-ManagerComfyUI-Easy-Use (by yolain)
https://github.com/yolain/ComfyUI-Easy-UseComfyUI_UltimateSDUpscale (by ssitu)
https://github.com/ssitu/ComfyUI_UltimateSDUpscaleComfyUI-Anima_LLLite (by kohya-ss)
https://github.com/kohya-ss/ComfyUI-Anima-LLLite
Experiment and enjoy!
Description
Upload from V3→V4
(This is not an exhaustive changelog)
General:
General improvements and bug fixes
Changed default values e.g. diffusion model is anima preview 3 now
Added CFGZeroStar option
Advanced:
Added Post Processing Group
Added Mask Detailer
Standard:
Added Post Processing Group
FAQ
Comments (25)
Where do we get all those detector/detailer ultralytics/yolo models? The ultralytics github page is confusing
basically, just make a new folder models/sams and models/ultralytics/segm + models/ultralytics/bbox and put the models in those folders
Hands (hand_yolov9c): https://huggingface.co/Bingsu/adetailer/blob/main/hand_yolov9c.pt
Face (face_yolov9c): https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt
Eye (Eyeful_v2-Paired or Eyeful_v2-Individual): https://civitai.com/models/178518/eyeful-or-robust-eye-detection-for-adetailer-comfyui
NSFW (ntd11_anime_nsfw_segm_v5-variant1): https://civitai.com/models/1313556/anime-nsfw-detectionadetailer-all-in-one
Body (yolo11m-seg): https://docs.ultralytics.com/models/yolo11/#segmentation-coco
@Legendaer will there be a controlnet workflows? or it doesnt exist? (im new to comfyui )
@monicalucci Anima is structurally different and thus needs new adapters to be made for it. Until then, try adding natural language to the end of your prompt or using img2img to see if you can get the results you want.
I'd like to tag this workflow when I post images, but I can't even do it manually because it doesn't show up in the filters!
Yeah, I don't know why Civitai doesn't allow workflows to be added like other resources, but you can either create a post on the workflow model page using the "Add post" button (scroll down to the gallery), or edit the workflow by expanding the Image Saver Metadata node and inserting the Civitai model hash into additional_hashes manually, e.g. "workflow:A4ADC54BD4". That way it will be recognized automatically when uploading the pictures to Civitai, just like the other metadata.
There seems to be some error in the advanced workflow: after upscaling, detailers work with the image before upscaling.
May I ask if there are any video tutorials or process demonstrations? I really need them, thank you
Could you create one for the standard/advanced workflow using the Power LoRA Loader (rgthree)? I find the LoRA Loader (LoraManager) a bit too complex, rgthree’s version is simpler and easier to use.
Is it possible to add regional prompting?
Why does any ADetailer keeps forever to finish?
I'm having a very odd issue. This workflow works perfectly fine for me but the lora loader doesn't seem to recognise SPECIFICALLY the anima loras I want to use. It sees all the others (in subfolders and out of them), but it skips all of the anima ones. I also spawned a regular lora loader node and there it immediately finds them. Anyone know why this happens or how to fix?
try update them from lora manager
I had this issue before, but I figured it out by going to the LoRA Loader extension. It opens in your browser, and you need to press “Refresh” and then “Fetch.” This will reload it in your workflow in ComfyUI. That’s why I prefer the rgthree Power LoRA Loader over LoraManager, but both have their own benefits after you’ve used them for a while.
@monicalucci cheers
Hello, would you tell how to add XY plot for your workflow ? :)
Question: on Comfy, where would I place the hand, face, and eye detectors?
/ComfyUI/models/ultralytics/bbox
the advanced workflow still upscales the non-detailed image
Hi, after updating ComfyUI to the latest version, the "Image Saver Simple" node stopped working in my "AnimaAdvancedV4" workflow. It consistently shows the error: "Required input is missing: images," even though the IMAGE input is correctly connected. Interestingly, my simpler workflows like "AnimaBasicV4" and "AnimaStandardV4" are still working fine with this node. Could you please check if there's a compatibility issue with more complex configurations? Thanks!
I have the same problem...
X3 Please help
im having this prob too. . problem kjnode extension needs an update. . .
@Legendaer help us please 😊🙏🏻