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) Not needed for newer ComfyUI Versions
https://github.com/kohya-ss/ComfyUI-Anima-LLLite
Experiment and enjoy!
Description
Upload from V4→V5
(This is not an exhaustive changelog)
General:
General improvements and bug fixes
Changed default values
Remove Body Detailer
Advanced:
Added Sam 3.1
Added Regional Prompting
FAQ
Comments (34)
Зачем так нагружено, официальной версии не хватает что ли?
do you have tips on how to use the regional prompting?
is any red/blue/green image with different size matter?
hope someone can do some brief tutorial 😅
I think it's currently broken idk
@Toadzonbe i saw on youtube there is a Multi-area condition node, looks neat, but not anima workflow though, not sure. . .
I have the exact same question! Aside from that, I'm also not quite sure what the 'load image' function is for, but the other restoration features in the workflow work like a charm.
following this thread - I've been able to do regional prompting in the past, but not clear how to use the RGB channels in the advanced workflow.
V4 not work but V5 works great! Let's try out its features and see how it goes. Thank you very much! 😊
Sorry, I don't know how to use I2I, but I uploaded an image and it's not working.
Why? I've already tried all three workflows and nothing works. Am I doing something wrong? 😅
I hope someone can help me. Thank you very much in advance! ✨🙏🏻
Hi, I've tested the AnimaAdvancedV5 and it's working perfectly now! Thanks for the fix and the update.
regional prompting no work :<
Is there any reason this would not work well with the base model that came out?
From my Testing at least. It works well with Base1.0 Anima
trying to upscale the image but it don't work and give this error:
Traceback (most recent call last):
File "D:\matrix\Data\Packages\ComfyUI\execution.py", line 535, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\matrix\Data\Packages\ComfyUI\execution.py", line 335, in get_output_data
return_values = await asyncmap_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\matrix\Data\Packages\ComfyUI\custom_nodes\comfyui-lora-manager\py\metadata_collector\metadata_hook.py", line 171, in async_map_node_over_list_with_metadata
results = await original_map_node_over_list(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\matrix\Data\Packages\ComfyUI\execution.py", line 309, in asyncmap_node_over_list
await process_inputs(input_dict, i)
File "D:\matrix\Data\Packages\ComfyUI\execution.py", line 297, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\matrix\Data\Packages\ComfyUI\custom_nodes\comfyui-kjnodes\nodes\nodes.py", line 937, in get_widget_value
raise ValueError("No matching node found for the given title or id")
ValueError: No matching node found for the given title or id
fixed it by changing node_id value from 22 to 481 (problem was in model loader id). but I still don't get it, in the workflow there is an option to upload an image, I thought it skips the image generation and gives me the opportunity to upscale the uploaded image, instead it starts generating a new one
maked it work with turned off ksampler
Great workflow, but lora loader isn't work for me
Did you click the lora manager next to your bookmarks in the ui? It'd been so long since I last clicked it that I honestly forgot it existed so it never occurred to me to click it until I started looking stuff up.
@Dakarn2389 I typed in lora's name, but it didn't show up. Only some other loras appeared. I also tried other workflows and their lora loader worked perfectly.
为何我完全运行不了这个，没有报错。点击运行只有0.2s的运行完成
缺少lora或者后面那几个节点里的模型
@GingerBorgia233 并不是，要回退版本
Would like to know if this workflow works if using Anima based-v1.0's clip and vae(through comfyUI's built-in model loader)?
BTW, thanks for your work, appreciate it.
Yes It does, Atleast according to my Testing, you can try for yourself
Hello there! Just wanted to Express Appreciation to this Workflow, Helped me a Lot and Gives me Bangers! Not to mention it works well on Base1 Anima, or atleast as I tested in an AnimaB1 Based Finetune, Thank you!
Whoa! V6 Already? Wasn't prepared for that!
Thanks for all your workflows
There some issue in workflows. The detailers work with image that not detailed with previous detailer. and the output image in the saver is image from the kSampler, not detailed at all. How i can fix that? (sorry for my english)
When I use Basic T2I, there are a lot of noise artifacts in the image after passing through the Detailer node. Why is that?
Hi,
Cool workflow, but I found a bug. The scheduler name was connected to the KSampler node and the Image Saver Metadata node on Denoise. It might be a problem unique to me, but after I disconnected the scheduler name and connected Denoise to both nodes, it worked perfectly. In case anyone else has the same problem, try downloading the workflow again or using this simple workaround.
the lora loader rghtree in the basic version works fine, but the lora loader in standard and advanced versions only detects 5 lora, what's the difference between the two?
it's probably a silly question, but I'm new to comfy
for Lora Loader (not rgthree) you have to open its extension and u need to refresh it from there in order for you to see the loras in your comfyui
@monicalucci Thanks bro, it worked! I didn't even know there was a Lora Manager tab.
very nice workflow !