Model Library / Wan 2.1 Text-to-Video 1.3B
Video
ComfyUI
Wan 2.1 Text-to-Video 1.3B
Lightweight open text-to-video model — 480p clips on a single GPU in minutes.
Overview
Wan 2.1 1.3B generates short 480p videos from text prompts. It is small enough to iterate quickly on an RTX 5090; use ComfyUI's built-in Wan workflow template.
Key features
- ✓Text-to-video
- ✓Runs comfortably in 32 GB
- ✓Apache 2.0
Use cases
- →Social media clips
- →Storyboarding
- →Video model research
On this template
Runs on the ComfyUI template, exposing its ComfyUI at a private HTTPS address. You also get root SSH and JupyterLab.
COMFY_DOWNLOADS | Comfy-Org/Wan_2.1_ComfyUI_repackaged|split_files/diffusion_models/wan2.1_t2v_1.3B_fp16.safetensors|diffusion_models;
Comfy-Org/Wan_2.1_ComfyUI_repackaged|split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors|text_encoders;
Comfy-Org/Wan_2.1_ComfyUI_repackaged|split_files/vae/wan_2.1_vae.safetensors|vae |
Quick start
- Click Deploy and pick an available GPU — only offers with enough VRAM are shown.
- Wait for the status to turn running. The first start downloads the model, which can take a few minutes.
- Use the connection details on your rental page:
Browser
Open https://r12-abcd1234-app.gpu.clearlayer.ca Gateway login: user edge password <app-token> Workflow → Browse Templates, pick the template for your model, Queue.