ThetaCursed/ComfyUI-MOSSImageTextEncoder
ComfyUI node that feeds a reference image through the Qwen3.5-9B vision tower and injects its embeddings into the text prompt (MOSS-Image conditioning)
GitHub repository with 46 stars and 9 forks.
Language: Python
Topics: comfyui, comfyui-nodes, image-condition, moss-image, text-encoder, vision, qwen3-5