Nodes/ComfyUI-VisionPromptAssistant/Abliteration Vision Prompt
ComfyUI Node

Abliteration Vision Prompt

Generates a prompt through Abliteration.ai's OpenAI-compatible vision API. Supports separate system/user prompts and up to three images. Images are resized and compressed before upload.

By elgalardi·Created 21 days ago·Updated a day ago· 1
Abliteration Vision Prompt
  • image_0
  • image_1
  • image_2
  • generated_text
  • usage_stats
  • credits_remaining
api_key
user_promptAnalyze the reference images and write a detailed MiniMax H3 generation prompt.
system_promptYou write production-ready prompts for MiniMax H3 Reference to Video. Use the exact supplied <Picture n> tags, clearly assigning identity, appearance, style, motion, and camera. Return only the final generation prompt.
max_tokens256
temperature0.40
thinkingfalse
seed0
image_max_dimension1024
timeout_seconds180
Categorytext

Inputs (12)

NameTypeDefaultDescription
api_keySTRINGAbliteration.ai API key. The interface masks this value, but a saved workflow may still contain it.
user_promptSTRINGAnalyze the reference images and write a detailed MiniMax H3 generation prompt.
system_promptSTRINGYou write production-ready prompts for MiniMax H3 Reference to Video. Use the exact supplied <Picture n> tags, clearly assigning identity, appearance, style, motion, and camera. Return only the final generation prompt.
max_tokensINT2561–4096
temperatureFLOAT0.400–2
thinkingBOOLEANfalseDisable for faster prompt enhancement.
seedINT00–4294967295
image_max_dimensionINT1024256–2048Images are resized to this maximum width or height before upload. Lower values are faster and cost fewer tokens.
timeout_secondsINT18015–600
image_0optIMAGE
image_1optIMAGE
image_2optIMAGE

Outputs (3)

NameTypeDescription
generated_textSTRING
usage_statsSTRING
credits_remainingSTRING