ComfyUI Node: Qwen2.5-VL Text Encoder (Advanced)

Authored by fblissjr

Created

Updated

174 stars

Category

QwenImage/Encoding

Inputs

clip CLIP
text *
mode
  • text_to_image
  • image_edit
  • multi_image_edit
  • inpainting
template_output QWEN_TEMPLATE
edit_image IMAGE
vae VAE
inpaint_mask MASK
system_prompt STRING
vae_max_dimension INT
debug_mode BOOLEAN
auto_label BOOLEAN
verbose_log BOOLEAN
resolution_mode
  • balanced
  • hero_first
  • hero_last
  • progressive
  • custom
  • memory_optimized
hero_weight FLOAT
reference_weight FLOAT
max_memory_mb INT
image_weights STRING
label_format
  • Picture
  • Image

Outputs

CONDITIONING

STRING

Extension: ComfyUI-QwenImageWanBridge

Custom nodes for bridging Qwen-Image and WAN video models in ComfyUI.

Authored by fblissjr

View Nodes

Run ComfyUI workflows in the Cloud!

No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues

Learn more