ComfyUI Node: StyleAligned Reference Sampler ♾️Mixlab

Authored by shadowcz007

Created

Updated

1589 stars

Category

♾️Mixlab/Style

Inputs

ref_latents STEP_LATENTS
reference_image_text STRING
model MODEL
clip CLIP
positive CONDITIONING
negative CONDITIONING
share_norm
  • both
  • group
  • layer
  • disabled
share_attn
  • q+k
  • q+k+v
  • disabled
scale FLOAT
batch_size INT
seed INT
steps INT
cfg FLOAT
scheduler
  • normal
  • karras
  • exponential
  • sgm_uniform
  • simple
  • ddim_uniform
  • beta
  • linear_quadratic
  • kl_optimal
denoise FLOAT

Outputs

LATENT

LATENT

Extension: comfyui-mixlab-nodes

3D, ScreenShareNode & FloatingVideoNode, SpeechRecognition & SpeechSynthesis, GPT, LoadImagesFromLocal, Layers, Other Nodes, ...

Authored by shadowcz007

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