Nodes/ComfyUI_EmAySee_CustomNodes/EmAySee_Qwen / OpenAI Prompt From Image
ComfyUI Node

EmAySee_Qwen / OpenAI Prompt From Image

A ComfyUI node in d3cker/Prompt-Generator with 18 inputs and 2 outputs.

By EmAySee·Created about a year ago·Updated 3 months ago· 2
EmAySee_Qwen / OpenAI Prompt From Image
  • image
  • prompt_text
  • thinking_text
backend
qwen_model
local_model_path
device
quantization
flash_attention
system_promptYou convert the given image into a rich, image-generation prompt. Return ONLY the final prompt as a single line, no quotes, no extra text. Include: subject, environment, style, lighting, camera/lens, composition, key details. Avoid meta-commentary.
user_prompt
max_new_tokens2048
temperature0.20
safe_quantstrue
unload_modeltrue
openai_base_urlhttp://127.0.0.1:11434
openai_api_key
openai_model_override
openrouter_providers
verbose_outputtrue
Categoryd3cker/Prompt-Generator

Inputs (18)

NameTypeDefaultDescription
imageIMAGE
backendCOMBO2 options: local, openai_compatible
qwen_modelCOMBO8 options: Qwen/Qwen2.5-VL-3B-Instruct, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen3-VL-2B-Instruct, Qwen/Qwen3-VL-2B-Thinking, Qwen/Qwen3-VL-8B-Instruct, Qwen/Qwen3-VL-8B-Thinking, +2
local_model_pathSTRING
deviceCOMBO1 options: cpu
quantizationCOMBO5 options: int8_bnb, int4_bnb, bf16, fp16, fp32_cpu
flash_attentionCOMBO2 options: off, on
system_promptSTRINGYou convert the given image into a rich, image-generation prompt. Return ONLY the final prompt as a single line, no quotes, no extra text. Include: subject, environment, style, lighting, camera/lens, composition, key details. Avoid meta-commentary.
user_promptSTRING
max_new_tokensINT204816–8192
temperatureFLOAT0.200–2
safe_quantsCOMBOtrue2 options: true, false
unload_modelCOMBOtrue2 options: true, false
openai_base_urloptSTRINGhttp://127.0.0.1:11434
openai_api_keyoptSTRING
openai_model_overrideoptSTRING
openrouter_providersoptSTRING
verbose_outputoptCOMBOtrue2 options: true, false

Outputs (2)

NameTypeDescription
prompt_textSTRING
thinking_textSTRING