Simple workflow with ControlNet tiled upscale
Runtime profile
Source description
Simple workflow with ControlNet tiled upscale
This is my main workflow for SDXL/Pony/Illustrious that uses ControlNet tile upscaling instead of Ultimate SD. Feel free to DM me if you have any questions about the workflow.
v1.2 update
Added CFG Skimming, after more testing I think it's an interesting tool. Can be easily disabled in generation settings options (enable_skimming). Change CFG to recommended checkpoint values when you disable it.
Saved images should now be compatible with Civitai. I was getting tired of filling some fields manually. Requires manual installation of Save Images With Metadata Universal Extension
Combined generation settings into a single subgraph
Sources
1 sourceSource excerpts
1 excerptSource context: 433 downloads · Type Workflows · Base model Illustrious
For MetaData saver to work properly, run Rules Scanner Subgraph once after installation or when you change nodes in ComfyUI (I don't make the rules)
By default set tile_batch_size to 1 in HiRes subgraph to safely run on https://huggingface.co/TTPlanet/TTPLanet_SDXL_Controlnet_Tile_Realistic
Alternative model for anime and stylized models - sharper and cleaner details: https://huggingface.co/xinsir/controlnet-union-sdxl-1.0
Put these models into ComfyUI/models/controlnet folder
KSampler can be replaced with a ComfyUI one, I'm using Inspire's node for different noise generation options.
Control upscale size and denoise in the HiRes subgraph
For higher upscale values (3-4x) use lower denoise (0.2 or even lower).
Custom Adetailer prompt
In Use custom prompt node set value to true and type positive/negative prompts which will be used for faces. Userful when some Loras overpower Adetailer and change face color too much, or if you just want to adjust face expression. With additional nodes you can set it up to use different Loras during this step. Increase feather value if you get visible edges around faces.
Low VRAM
To save VRAM inside a HiRes Upscale subgraph try this:
In Tiled Diffustion node Set batch size to 1. This will reduce VRAM load considerably at the cost of speed.
Set VAE Decode tile size to 512.
If it's still VRAM hungry, try setting tile width/height in Tiled Diffusion and VAE encode to 512x512. Might want to change overlap as well, but I haven't tested this.
Remaining hardware or download-size estimates are not available yet.
Requirements
Object Detector · 49.6 MB · Hugging Face · Bingsu/adetailer
LoRA · 218 MB · SAFETENSORS · Hugging Face · chilkersion/freckledvixon
broken_android_0.2.safetensors
Not resolvedLoRA · Unknown
ck-Sommo-Concept-Art-IL-000012.safetensors
Not resolvedLoRA · Unknown
ForestILL.safetensors
Not resolvedLoRA · Unknown
glinty_v1.safetensors
Not resolvedCheckpoint · Unknown
GOBOLightingILL.safetensors
Not resolvedLoRA · Unknown
Upscaler · 63.8 MB · SAFETENSORS · Civitai · 147759
ControlNet · 2.33 GB · Hugging Face · TTPlanet/TTPLanet_SDXL_Controlnet_Tile_Realistic
ComfyMath
PossibleNode pack · Registry
comfyui-impact-pack
FoundNode pack · Registry
comfyui-impact-subpack
FoundNode pack · Registry
Node pack · Registry
Node pack · Registry
ComfyUI-TiledDiffusion
FoundNode pack · Registry