Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This workflow uses kontext dev together with Deblur LoRA; the prompts in the workflow maximize consistency of a character’s appearance, but because the control can be too strong it often fails to high‐res the image....
Runtime profile
Source description
This workflow uses kontext dev together with Deblur LoRA; the prompts in the workflow maximize consistency of a character’s appearance, but because the control can be too strong it often fails to high‐res the image. In that case you need to adjust the “Deblur lora strength” and “Flux Guidance” values, and you may even need to increase the CFG value.
Note: this workflow cannot restore old, damaged photos.
Remaining hardware or download-size estimates are not available yet.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use “Kontext Image enlargement without distortion” to enlarge an image while keeping a character’s appearance consistent. It uses kontext dev and Deblur LoRA, with a high-resolution enlargement as the intended output.
It combines kontext dev with Deblur LoRA, and its prompts maximize consistency of a character’s appearance.
The control can be too strong, so high-resolution processing may fail.
Input: an image. Intended output: a high-resolution enlargement with consistent character appearance.
Find it on Civitai at https://civitai.com/models/1886884. It is published by BBS Revenger and uses Flux.1 Kontext as its base model.
Node packs listed for the workflow: cg-use-everywhere, comfyui_faceanalysis, comfyui-custom-scripts, comfyui-easy-use, and rgthree-comfy.
Model files listed: 2xNomosUni_esrgan_multijpg.pth, ae.safetensors, clip_l.safetensors, Flux_kontext_deblurB.safetensors, and flux1-krea-dev.safetensors.
Additional model files listed: kontextNsfwFp8_kontextNsfwFp8-C.safetensors, OpenFLUX.1-vae.safetensors, SkinTextureRealisticDetailed.safetensors, t5xxl_fp16.safetensors, and t5xxl_fp8_e4m3fn_scaled.safetensors.
If high-resolution processing fails, adjust “Deblur lora strength” and “Flux Guidance”; increasing CFG may also be needed.
Suggestion · not verified
It cannot restore old, damaged photos.
Before using it, verify that these files are available: Flux_kontext_deblurB.safetensors, kontextNsfwFp8_kontextNsfwFp8-C.safetensors, SkinTextureRealisticDetailed.safetensors, OpenFLUX.1-vae.safetensors, and 2xNomosUni_esrgan_multijpg.pth.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 741 downloads · Type Workflows · Base model Flux.1 Kontext
Requirements
2xNomosUni_esrgan_multijpg.pth
Not resolvedUpscaler · Unknown
VAE · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged · Lumina Image 2.0 Repackaged
Text encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
Flux_kontext_deblurB.safetensors
Not resolvedLoRA · Unknown
flux1-krea-dev.safetensors
Not resolvedCheckpoint · Unknown
kontextNsfwFp8_kontextNsfwFp8-C.safetensors
Not resolvedCheckpoint · Unknown
OpenFLUX.1-vae.safetensors
Not resolvedVAE · Unknown
SkinTextureRealisticDetailed.safetensors
Not resolvedLoRA · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
t5xxl_fp8_e4m3fn_scaled.safetensors
File unverifiedText encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
cg-use-everywhere
FoundNode pack · Registry
comfyui_faceanalysis
FoundNode pack · Registry
comfyui-custom-scripts
FoundNode pack · Registry
comfyui-easy-use
Node pack · Registry
rgthree-comfy
FoundNode pack · Registry
