Nodes/Eric_Qwen_Edit_Experiments/Eric Qwen-Edit Style Transfer
ComfyUI Node

Eric Qwen-Edit Style Transfer

A ComfyUI node in Eric Qwen-Edit with 17 inputs and 1 output.

By EricRollei·Created 5 months ago·Updated 3 months ago· 19
Eric Qwen-Edit Style Transfer
  • pipeline
  • style_image
  • content_image
  • image
style_modefull_style
custom_prompt
additional_guidance
style_strength1.0
vae_target_size1024
vl_styletrue
vl_contenttrue
ref_stylefalse
ref_contenttrue
negative_promptblurry, distorted, low quality
steps8
true_cfg_scale4.0
seed0
max_mp8.0
CategoryEric Qwen-Edit

Inputs (17)

NameTypeDefaultDescription
pipelineQWEN_EDIT_PIPELINE
style_imageIMAGEReference image providing the style (passed as Picture 1)
content_imageIMAGEImage to apply the style to (passed as Picture 2)
style_modeCOMBOfull_styleType of style transfer to apply
custom_promptoptSTRINGWhen non-empty, overrides the style_mode template entirely. Reference images as Picture 1 (style) and Picture 2 (content).
additional_guidanceoptSTRINGExtra instructions appended to the style prompt (e.g., 'but keep faces realistic')
style_strengthoptFLOAT1.00.1–2How strongly to apply the style (affects CFG emphasis). 1.0=balanced, >1=stronger style, <1=more original content
vae_target_sizeoptINT10240–2048Fixed resolution for VAE encoding. 0 (default) = encode refs at output resolution (matches Edit node behavior, best for high-res). Set to e.g. 1024 to force refs to ~1MP (only useful at low output res).
vl_styleoptBOOLEANtrueInclude style image in VL/semantic path (text encoder sees its content)
vl_contentoptBOOLEANtrueInclude content image in VL/semantic path
ref_styleoptBOOLEANfalseInclude style image in VAE/ref path (pixel-level latent). Default False — style is semantic-only, preventing structure bleed.
ref_contentoptBOOLEANtrueInclude content image in VAE/ref path (preserves its pixel structure)
negative_promptoptSTRINGblurry, distorted, low qualityWhat to avoid
stepsoptINT81–100Inference steps (8 for lightning LoRA, 50 for base model)
true_cfg_scaleoptFLOAT4.01–20True CFG scale
seedoptINT00–18446744073709550000Random seed
max_mpoptFLOAT8.00.5–16Max output megapixels. VAE refs scale to match output resolution.

Outputs (1)

NameTypeDescription
imageIMAGE