ComfyUI Node: Text-to-Image Prompt Enhancer

Authored by EricRollei

Created

Updated

38 stars

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

Eric Prompt Enhancers

Inputs

text_prompt STRING
reference_directive_1
  • none
  • auto
  • recreate
  • reinterpret
  • subject only
  • style only
  • lighting only
  • composition
  • genre
reference_directive_2
  • none
  • auto
  • recreate
  • reinterpret
  • subject only
  • style only
  • lighting only
  • composition
  • genre
prompt_context
  • none
  • auto
  • expand_short_prompt
  • finish_opening_line
  • prompt_from_item_list
  • modify_reference_image
  • enhance_reference_image
creative_randomness
  • auto
  • none
  • off
  • subtle
  • moderate
  • bold
  • storyteller
  • chaotic
target_platform
  • flux
  • flux_kontex
  • sd_xl
  • sd_1_5
  • pony
  • illustrious
  • chroma
  • pixart_sigma
  • aura_flow
  • noobai
  • kolors
  • qwen_image
  • qwen_image_edit
  • wan_image
llm_backend
  • lm_studio
  • ollama
  • qwen3_vl
api_endpoint STRING
temperature FLOAT
vision_backend
  • auto
  • lm_studio
  • ollama
  • qwen3_vl
  • disable
vision_api_endpoint STRING
camera_angle
  • auto
  • random
  • none
  • eye level
  • low angle
  • high angle
  • dutch angle
  • bird's eye view
  • worm's eye view
  • over the shoulder
  • point of view
  • extreme close-up angle
composition
  • auto
  • random
  • none
  • rule of thirds
  • centered
  • symmetrical
  • asymmetrical
  • golden ratio
  • leading lines
  • frame within frame
  • negative space
  • balanced
  • dynamic diagonal
lighting_source
  • auto
  • random
  • none
  • natural sunlight
  • studio lighting
  • golden hour sun
  • moonlight
  • candlelight
  • neon lights
  • firelight
  • spotlight
  • ambient lighting
  • backlight
  • rim lighting
  • window light
  • street lights
lighting_quality
  • auto
  • random
  • none
  • soft diffused
  • hard dramatic
  • even balanced
  • high contrast
  • low key
  • high key
  • chiaroscuro
  • volumetric
  • atmospheric
time_of_day
  • auto
  • random
  • none
  • dawn
  • early morning
  • mid-morning
  • noon
  • afternoon
  • golden hour
  • dusk
  • twilight
  • night
  • midnight
  • blue hour
historical_period
  • auto
  • random
  • none
  • prehistoric era
  • ancient civilizations
  • classical antiquity
  • medieval era
  • renaissance
  • baroque period
  • industrial revolution
  • victorian era
  • edwardian era
  • roaring twenties
  • mid-century modern
  • 1960s counterculture
  • 1980s neon wave
  • 1990s digital dawn
  • modern day
  • near future
  • far future
  • cyberpunk future
  • post-apocalyptic era
  • fantasy realm
  • science fiction epoch
weather
  • auto
  • random
  • none
  • clear sky
  • partly cloudy
  • overcast
  • misty
  • foggy
  • rainy
  • stormy
  • snowy
  • sunny
  • hazy
art_style
  • auto
  • none
  • photorealistic
  • digital art
  • oil painting
  • watercolor
  • anime
  • manga
  • sketch
  • pencil drawing
  • 3D render
  • illustration
  • concept art
  • impressionist
  • abstract
  • pixel art
  • low poly
  • papercraft
  • isometric
genre_style
  • auto
  • random
  • none
  • surreal
  • cinematic
  • dramatic
  • action
  • humorous
  • indie
  • horror
  • scifi
  • romantic
  • x-rated
  • pg
  • artistic
  • documentary
  • minimalist
  • maximalist
  • vintage
  • modern
  • fantasy
  • noir
  • cyberpunk
  • steampunk
  • dieselpunk
  • mythic
  • gothic
  • art deco
  • retro futurism
color_mood
  • auto
  • random
  • none
  • vibrant
  • muted
  • monochrome
  • warm tones
  • cool tones
  • pastel
  • high contrast
  • desaturated
  • neon
  • earth tones
subject_framing
  • auto
  • random
  • none
  • extreme close-up
  • close-up
  • medium close-up
  • medium shot
  • medium wide
  • wide shot
  • full body
  • cowboy shot
  • bust shot
  • head and shoulders
  • three-quarter
  • establishing shot
  • aerial overview
  • profile view
subject_pose
  • auto
  • random
  • none
  • standing
  • sitting
  • lying down
  • kneeling
  • crouching
  • action pose
  • portrait pose
  • dynamic
  • static
  • asymmetric
  • contrapposto
  • relaxed
  • tense
  • walking
  • running
  • jumping
  • dancing
  • floating
positive_keywords STRING
negative_keywords STRING
seed_mode
  • random
  • fixed
  • increment
  • decrement
random_seed INT
save_to_file BOOLEAN
filename_base STRING
reference_image_1 IMAGE
reference_image_2 IMAGE
reference_caption_override_1 STRING
reference_caption_override_2 STRING

Outputs

STRING

STRING

STRING

STRING

STRING

INT

Extension: Eric's Prompt Enhancers for ComfyUI

A comprehensive suite of AI-powered prompt enhancement nodes for ComfyUI using local LLMs (LM Studio or Ollama). Transform simple prompts into detailed, platform-optimized descriptions for video and image generation.

Authored by EricRollei

Looking for a different node?

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.

Learn more