Inject up to 6 reference images into conditioning for FLUX.2 (and other edit models consuming reference_latents) in a single node. Each image has its own strength (0 = skip), built-in VAE encode, all inputs optional so one static workflow covers 0–6 references without bypass or rewiring. Independent implementation based on ComfyUI's public native ReferenceLatent mechanism.
6 lines
256 B
Python
6 lines
256 B
Python
"""comfyui_multi_referencelatent — 多参考图 latent 注入节点(FLUX.2 等编辑模型)。"""
|
|
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
|
|
|
|
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
|
|
WEB_DIRECTORY = "./web"
|