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:
馃煡Anima: Standard workflow version
馃煥AnimaStandard: more simplistic version of the workflow
馃煩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 V5鈫扸6
(This is not an exhaustive changelog)
General:
General improvements and bug fixes
Changed default values
Remove Body Detailer
Advanced:
Added ControlNet LLLite
Detailer:
New Workflow for Detailing/Upscaling/Inpainting Images
FAQ
Comments (15)
It's nice, but way too cluttered. With the right settings and the right prompt, a lot of what's in your workflow is completely unnecessary and just slows down the whole process ^^
what's your recommend workflow to run it smoothly or simplified version if you dont mind sharing
@monicalucci聽Well, I do have a few nodes in my workflow, but the Face Detailer, Hand Detailer, etc. are actually unnecessary. With my workflow, it takes me about 25 seconds per image, but even testing with the absolute basic workflows that ComfyUI offers works pretty well. The magic lies in the samplers, schedulers, and the Detailer Loras鈥攐nce you鈥檝e set those up correctly for yourself, you鈥檒l rarely have issues with errors in the images :)
When I get around to it, I鈥檒l post a simplified version of my workflow online without my custom nodes ^^
I am getting this error when running V6 workflows:
## Error Details -
Node ID: 35 -
Node Type: Image Saver Simple -
Exception Type: TypeError -
Exception Message: TypeError: object of type 'NoneType' has no len()
try update your comfyui
It prompts you that there are no images save VAE Decode connect Image saver simple
hey bud, thanks for the workflows, again, haha. Could you add outpaint to the anima detailer? it would be awesome!
did u find an outpaint workflow?
Is there a guide to the bbox section? The hand/face/eyes etc? Getting a little lost on the standard variant in that specific area. Thank you so much for the workflows!
nice work!
Thanks to the author. WF helped me understand the details of working with the model.
will there be a support for NegPiP?
I am getting errors with regional prompting while having the detailers enabled. Not sure if thats intended. If I disable them I do get a good output.
Why, when I use this workflow, do male penises or female vaginas always turn into a solid white patch? Where is the setting wrong?
Have you tried typing censor into the neg prompt?