Nodes/ComfyUI-QwenVL/QwenVL (HF Alt)
ComfyUI Node

QwenVL (HF Alt)

A ComfyUI node in 🧠aistudynow/QwenVL with 10 inputs and 1 output.

By aistudynow·Created 10 months ago·Updated 4 months ago· 15
QwenVL (HF Alt)
  • image
  • video
  • RESPONSE
model_nameQwen3-VL-2B-Instruct
quantizationNone (FP16)
attention_modeauto
preset_prompt🖼️ Detailed Description
custom_prompt
max_tokens512
keep_model_loadedtrue
seed1
Category🧠aistudynow/QwenVL

Inputs (10)

NameTypeDefaultDescription
model_nameCOMBOQwen3-VL-2B-InstructPick the Qwen-VL checkpoint. First run downloads weights into models/LLM/Qwen-VL, so leave disk space.
quantizationCOMBONone (FP16)Precision vs VRAM. FP16 gives the best quality if memory allows; 8-bit suits 8–16 GB GPUs; 4-bit fits 6 GB or lower but is slower.
attention_modeCOMBOautoauto tries flash-attn v2 when installed and falls back to SDPA. Only override when debugging attention backends.
preset_promptCOMBO🖼️ Detailed DescriptionBuilt-in instruction describing how Qwen-VL should analyze the media input.
custom_promptSTRINGOptional override—when filled it completely replaces the preset template.
max_tokensINT51264–2048Maximum number of new tokens to decode. Larger values yield longer answers but consume more time and memory.
keep_model_loadedBOOLEANtrueKeeps the model resident in VRAM/RAM after the run so the next prompt skips loading.
seedINT11–4294967295Seed controlling sampling and frame picking; reuse it to reproduce results.
imageoptIMAGE
videooptIMAGE

Outputs (1)

NameTypeDescription
RESPONSESTRING