Comfy-agent curated_vibevoice_1_5b_6gb_vram
name: curated_vibevoice_1_5b_6gb_vram
git clone https://github.com/steliosot/comfy-agent
skills/workflows/audio/curated_vibevoice_1_5b_6gb_vram/skill.yamlname: curated_vibevoice_1_5b_6gb_vram description: Curated workflow wrapper for VibeVoice 1.5B - 6GB VRAM.json inputs: prompt: type: string required: false negative_prompt: type: string required: false width: type: integer required: false height: type: integer required: false seed: type: integer required: false steps: type: integer required: false cfg: type: number required: false sampler_name: type: string required: false scheduler: type: string required: false denoise: type: number required: false server: type: string required: false headers: type: object required: false api_prefix: type: string required: false outputs: status: type: string prompt_id: type: string output_images: type: array requirements: models: [] custom_nodes:
- vibevoice-comfyui links:
- https://discord.com/invite/gggpkVgBf3
- https://github.com/Enemyx-net/VibeVoice-ComfyUI
- https://huggingface.co/Qwen/Qwen2.5-1.5B/tree/main
- https://huggingface.co/microsoft/VibeVoice-1.5B/tree/main
- https://www.youtube.com/@pixaroma input_modalities:
- audio output_modalities:
- audio/wav model_families:
- other node_count: 4 node_types:
- LoadAudio
- MarkdownNote
- SaveAudio
- VibeVoiceSingleSpeakerNode selection_metadata: family: audio resource_profile: medium complexity_score: 3 estimated_runtime: moderate (about 30-120s depending on server) warnings:
- Audio generation may take longer on CPU-only or low-VRAM servers.
- Uses custom nodes; missing nodes can cause validation/runtime failures. max_width: null max_height: null max_steps: null