Comfy-agent workflow_wan_2_2_i2v_14b

name: workflow_wan_2_2_i2v_14b description: Workflow wrapper for Wan 2.2 I2V 14B.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: clip name: umt5_xxl_fp8_e4m3fn_scaled.safetensors target_folder: models/clip
• type: vae name: wan_2.1_vae.safetensors target_folder: models/vae
• type: diffusion_model name: wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors target_folder: models/diffusion_models
• type: diffusion_model name: wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors target_folder: models/diffusion_models custom_nodes:
• comfyui-videohelpersuite links:
• https://discord.com/invite/gggpkVgBf3
• https://docs.comfy.org/tutorials/video/wan/wan2_2
• 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/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors?download=true
• https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors?download=true
• https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models
• https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B
• https://www.youtube.com/@pixaroma input_modalities:
• image
• text_prompt output_modalities:
• video/mp4 model_families:
• sd3
• wan node_count: 18 node_types:
• CLIPLoader
• CLIPTextEncode
• KSamplerAdvanced
• Label (rgthree)
• LoadImage
• MarkdownNote
• ModelSamplingSD3
• UNETLoader
• VAEDecode
• VAELoader
• VHS_VideoCombine
• WanImageToVideo selection_metadata: family: video_t2v_i2v_avatar resource_profile: very_high complexity_score: 9 estimated_runtime: heavy (can exceed 6 min; best on high-VRAM GPU) 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: null