ComfyUI Node: KG Krea 2 Image Guide Card V10
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
advanced/conditioning
Inputs
- manual tuning
- balanced
- keep the same subject
- copy pose and layout
- copy lighting and mood
- suggest the visual style
- suggest material or texture
- copy big shapes only
- avoid copying text/logos
- suggest the color palette
- use the background/setting
- copy the camera framing
- mood board only
- borrow drawing medium
- borrow photo finish
- borrow the clothing style
- borrow the era print look
- borrow the metallic accents
- borrow the ornament borders
- borrow the paper and canvas
- borrow the pattern energy
- borrow the poster style
- borrow the soft media look
- borrow the stained glass look
- borrow the weather
- carry the subject over
- cinematic color grade
- match the atmosphere
- match the monochrome look
- match the scene light
- style the finish only
- style the layout first
- use the background only
- overall image
- colors and art style
- color palette only
- pose, camera, and layout
- camera/framing only
- same person/product/object
- background/environment
- lighting and shadows
- mood-board only
- surface/material only
- big shapes only
- avoid words/logos
- use image as-is
- remove color
- soften tiny details
- blur words and texture
- palette wash
- color wash
- shape-only cleanup
- strong shape cleanup
- use stack setting
- low - loose idea (256)
- medium - balanced default (384)
- high - more exact (512)
- very high - most exact (768)
- use stack setting
- keep full image shape
- center crop square
- stretch to square
- recipe decides
- avoid copying subject
- allow subject if useful
- preserve same subject
- toward this image
- away from this image
- recipe decides
- whole image
- early layout only
- final details only
Outputs
KG_KREA_REFERENCE
Extension: ComfyUI Krea Reference
Give each reference image a job, and every attribute a dial. Guide cards assign per-image roles (keep the same subject, suggest the visual style, copy lighting or pose, big shapes only, avoid copying text/logos) with per-card strength, timing, and user-defined recipes - and Concept Slider cards turn any attribute you can name (brightness, age, fog density) into a training-free -6..+6 dial derived from Krea 2 text encoding.
Authored by kgilper
Looking for a different node?
More nodes in ComfyUI Krea Reference
Other advanced/conditioning nodes
- AQ_TextEncodeQwenImageEdit
- AQ_TextEncodeQwenImageEditPlus
- CLIPMicroConditioning
- Conditioning Multiply Advanced
- Conditioning Noise Injection
- Conditioning set timestep from sigma
- Conditioning Timestep Switch
- ConditioningZeroOut (Combine)
- CrossAttn_EraseReplace_HiDream
- EmAySee_TextEncodeQwenImageEdit_noRS
- EmAySee_TextEncodeQwenImageEditPlus_noRS
- Painter Flux Image Edit
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.