Workflow Wan 2 1 Text To Video 14b 480p And 720p

workflow_wan_2_1_text_to_video_14b_480p_and_720p

Imported workflow skill generated from Wan 2.1 Text to Video 14B 480p and 720p.json.

Family

• video_t2v_i2v_avatar

Inputs

• Optional runtime overrides supported by run(...):
  • prompt
  • negative_prompt
  • width, height
  • seed, steps, cfg
  • sampler_name, scheduler, denoise
  • server, headers, api_prefix

Outputs

• Returns JSON with:
  • status
  • prompt_id
  • output_images

Model Requirements

• clip: umt5_xxl_fp8_e4m3fn_scaled.safetensors -> models/clip
• diffusion_model: wan2.1-t2v-14b-Q8_0.gguf -> models/diffusion_models
• vae: wan_2.1_vae.safetensors -> models/vae

Custom Node Requirements

• comfyui-videohelpersuite

Links

• https://discord.com/invite/gggpkVgBf3
• 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/city96/Wan2.1-T2V-14B-gguf/resolve/main/wan2.1-t2v-14b-Q8_0.gguf?download=true
• https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/tree/main
• https://www.youtube.com/@pixaroma

Routing Metadata

• Family: video_t2v_i2v_avatar
• Input modalities: text_prompt
• Output modalities: video/mp4
• Model families: wan
• Node count: 11
• Complexity score: 8
• Resource profile: high
• Estimated runtime: slow (often 2-6 min depending on model/server load)
• Max latent resolution hint: 832x480
• Max sampler steps hint: 30

Detected Models

• clip: umt5_xxl_fp8_e4m3fn_scaled.safetensors -> models/clip
• diffusion_model: wan2.1-t2v-14b-Q8_0.gguf -> models/diffusion_models
• vae: wan_2.1_vae.safetensors -> models/vae

Detected Custom Nodes

• comfyui-videohelpersuite

Runtime 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.