Wan 2.1 text-to-video (1.3B)

Text-to-video with Wan 2.1's small 1.3B model, consumer-GPU friendly.

Estimated VRAM

~8.19 GB @ 480p — ✅ verified official figure. Wan2.1 README: 'The T2V-1.3B model requires only 8.19 GB VRAM' (5s 480P on RTX 4090, reference implementation). Source, checked 2026-10-13.

Models required

• wan2.1_t2v_1.3B_fp16.safetensors — 2.838 GB ✅ verified 2026-10-13 (listing) · sha256 be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5 → models/diffusion_models
• umt5_xxl_fp8_e4m3fn_scaled.safetensors — 6.736 GB ✅ verified 2026-10-13 (listing) · sha256 c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68 → models/text_encoders
• wan_2.1_vae.safetensors — 0.254 GB ✅ verified 2026-10-13 (listing) · sha256 2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b → models/vae

Tested GPUs

RTX 4090 (official README) ✅

Nodes

UNETLoader CLIPLoader VAELoader EmptyHunyuanLatentVideo KSampler VAEDecode SaveAnimatedWEBP

Common errors & fixes

Wrong CLIP type

Set CLIPLoader type to 'wan'. ⚠️ unverified: Fix is general guidance; not confirmed against the cited source.

Low-VRAM tips

⚠️ General guidance, not individually verified.

• Stay at 480p
• Fewer frames

Source & credit

Workflow by comfyanonymous (ComfyUI_examples) / Wan team. Get it from the original: https://comfyanonymous.github.io/ComfyUI_examples/wan/. License: Wan 2.1: Apache-2.0.