Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Added separate model loaders and an AIO Model Loader exclusively for the USDU group.
Runtime profile
Source description
Added:
Added separate model loaders and an AIO Model Loader exclusively for the USDU group.
If the AIO Model Loader group is toggled on, it will override the other loaders in the USDU group.
Disconnected the connections going into the tile settings on USDU. These will need to be set manually.
Removed:
The standard upscale with model related nodes have been removed. I am no longer using these and they are just adding more clutter for me at this point. The remaining options are the standard upscale image node with no upscale model attached and the SeedVR2 option.
Other notes:
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ComfyUI workflow to create images with the Anima model from text prompts or an input image, then upscale, detail, and color-correct them; it supports multiple LoRA loading and saves the resulting images.
The upscale and detailer stages have separate checkpoint, CLIP, and LoRA loaders.
The publisher removed the standard upscale-with-model nodes; the listed choices are the standard upscale image node without an upscale model attached and SeedVR2.
Saved images are described as including full metadata in a CivitAI-readable format.
Before using USDU, set the tile settings connections manually; the publisher says they are disconnected.
The listed node packs are ComfyMath, comfyui_ultimatesdupscale, comfyui-custom-scripts, comfyui-easycolorcorrector, comfyui-image-saver, comfyui-impact-pack, comfyui-impact-subpack, comfyui-inspire-pack, comfyui-kjnodes, and rgthree-comfy.
The two workflow files list these model names: animaElement7Model_nexusPrismIII.safetensors, Anzhc Face seg 1024 v2 y8n.pt, bbox/Eyeful_v2-Individual.pt, bbox/hand_yolov8s.pt, qwen_3_06b_base.safetensors, qwen_image_vae.safetensors, qwen3vl_4b_fp8_scaled.safetensors, sam_vit_b_01
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 1054 downloads · Type ComfyWorkflows · Base model Anima
I included a 'variant' version that has the settings I use when using Krea 2 Turbo in USDU.
I am not sure how many people who use my workflows actually use AIO models, but I will probably be removing these in the future.
Remaining hardware or download-size estimates are not available yet.
Requirements
animaElement7Model_nexusPrismIII.safetensors
Not resolvedCheckpoint · Unknown
Anzhc Face seg 1024 v2 y8n.pt
Not resolvedObject Detector · Unknown
Object Detector · 21.5 MB · Hugging Face · LeFeujitif/sandbox
Object Detector · Hugging Face
qwen_3_06b_base.safetensors
Not resolvedText encoder · Unknown
VAE · 242 MB · SAFETENSORS · Unknown
Text encoder · 4.88 GB · SAFETENSORS · Unknown
sam_vit_b_01ec64.pth
File unverifiedSegmentation · Unknown
seedvr2_3b_int8_convrot.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/SeedVR2
seedvr2_ema_vae_fp16.safetensors
File unverifiedVAE · Hugging Face · Comfy-Org/SeedVR2
Checkpoint · 5.24 GB · Civitai · 2430439
ComfyMath
PossibleNode pack · Registry
comfyui_ultimatesdupscale
FoundNode pack · Registry
comfyui-custom-scripts
FoundNode pack · Registry
Node pack · Registry
comfyui-image-saver
FoundNode pack · Registry
comfyui-impact-pack
FoundNode pack · Registry
comfyui-impact-subpack
FoundNode pack · Registry
Node pack · Registry
Node pack · Registry
rgthree-comfy
FoundNode pack · Registry
