Nodes/ComfyUI_MS_Diffusion/MS-Diffusion Conditioning (Native)
ComfyUI Node

MS-Diffusion Conditioning (Native)

Build MS-Diffusion image prompt tokens from CLIP-Vision penultimate hidden states + CLIP-L phrase pooled embeddings + layout boxes. Connect prompt_clean to your positive CLIPTextEncode so the two match.

By smthemex·Created 2 years ago·Updated 10 days ago· 58
MS-Diffusion Conditioning (Native)
  • ms_adapter
  • clip
  • clip_vision_output
  • ms_embeds
  • prompt_clean
◄promptbest quality, high quality, a [dog] on the beach►
◄boxes0.25, 0.25, 0.75, 0.75►
◄mask_threshold0.50►
◄drop_grounding_tokensfalse►
CategoryMSdiffusion/Native

Inputs (7)

NameTypeDefaultDescription
ms_adapterMS_ADAPTER—
clipCLIP—
clip_vision_outputCLIP_VISION_OUTPUT—
promptSTRINGbest quality, high quality, a [dog] on the beach—
boxesSTRING0.25, 0.25, 0.75, 0.75one 'x1,y1,x2,y2' per subject, separated by ';'. Ignored when mask_threshold is 0.
mask_thresholdFLOAT0.500–10 disables layout guidance entirely (upstream behaviour). >0 enables box guidance + pseudo attention mask.
drop_grounding_tokensBOOLEANfalse—

Outputs (2)

NameTypeDescription
ms_embedsMS_EMBEDS—
prompt_cleanSTRING—