Nodes/ComfyUI Razv WaveSpeed Nodes/WaveSpeedAI Qwen Image Text-to-Image LoRA
ComfyUI Node

WaveSpeedAI Qwen Image Text-to-Image LoRA

A ComfyUI node in WaveSpeedAI with 11 inputs and 1 output.

By razvanmatei-sf·Created 11 months ago·Updated 8 months ago· 0
WaveSpeedAI Qwen Image Text-to-Image LoRA
  • client
  • output_image
prompt
size1:1 (Square)
seed-1
output_formatjpeg
enable_sync_modetrue
lora_1_path
lora_1_scale1.0
lora_2_path
lora_2_scale1.0
custom_size
CategoryWaveSpeedAI

Inputs (11)

NameTypeDefaultDescription
clientWAVESPEED_AI_API_CLIENT
promptSTRINGText prompt for image generation (e.g., 'Realism, a female inventor with auburn hair...')
sizeCOMBO1:1 (Square)The aspect ratio and resolution of the generated image
seedINT-1-1–18446744073709550000Random seed for reproducible results. -1 for random seed
output_formatCOMBOjpegThe format of the output image
enable_sync_modeBOOLEANtrueWait for image generation to complete before returning
lora_1_pathoptSTRINGFirst LoRA model path (e.g., 'flymy-ai/qwen-image-realism-lora')
lora_1_scaleoptFLOAT1.00–2First LoRA influence scale (0.0 to 2.0)
lora_2_pathoptSTRINGSecond LoRA model path (optional)
lora_2_scaleoptFLOAT1.00–2Second LoRA influence scale (0.0 to 2.0)
custom_sizeoptSTRINGCustom size as 'width*height' (e.g. '1920*1080'). Overrides size dropdown if provided.

Outputs (1)

NameTypeDescription
output_imageIMAGE