Comfy-agent workflow_ep49_wan2_2_1_vace_gguf_text_to_video

name: workflow_ep49_wan2_2_1_vace_gguf_text_to_video description: Workflow wrapper for Ep49 Wan2 2.1 Vace GGUF Text To Video.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:

• type: diffusion_model name: Wan2.1-VACE-14B-Q4_K_M.gguf target_folder: models/diffusion_models
• type: clip name: umt5_xxl_fp8_e4m3fn_scaled.safetensors target_folder: models/clip
• type: vae name: wan_2.1_vae.safetensors target_folder: models/vae custom_nodes:
• comfyui-gguf links:
• https://discord.com/invite/gggpkVgBf3
• https://docs.comfy.org/tutorials/video/wan/vace
• https://github.com/ali-vilab/VACE
• https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp16.safetensors?download=true
• https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors?download=true
• https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors?download=true
• https://huggingface.co/QuantStack/Wan2.1-VACE-14B-GGUF/resolve/main/Wan2.1-VACE-14B-Q4_K_M.gguf?download=true
• https://huggingface.co/QuantStack/Wan2.1-VACE-14B-GGUF/tree/main
• https://www.youtube.com/@pixaroma input_modalities:
• text_prompt output_modalities:
• video/mp4 model_families:
• sd3
• wan node_count: 14 node_types:
• CLIPLoader
• CLIPTextEncode
• CreateVideo
• KSampler
• MarkdownNote
• ModelSamplingSD3
• SaveVideo
• TrimVideoLatent
• UnetLoaderGGUF
• VAEDecode
• VAELoader
• WanVaceToVideo selection_metadata: family: video_t2v_i2v_avatar resource_profile: high complexity_score: 8 estimated_runtime: slow (often 2-6 min depending on model/server load) warnings:
• Large model(s) detected; ensure enough VRAM and disk space.
• Uses custom nodes; missing nodes can cause validation/runtime failures.
• 'Video workflow: usually slower and VRAM-intensive than still-image workflows.' max_width: null max_height: null max_steps: 20