How to deploy Wan2.2-TI2V-5B on a GPU cloud
A 5B-parameter text/image-to-video model that runs on a consumer 4090. Full specs, license and use cases.
Wan2.2-TI2V-5B size and hardware requirements
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 18.6 GB | 22.4 GB | RTX 6000 | 1 | $0.173/hr |
| FP8 (quantized) | 4.7 GB | 5.6 GB | RTX 4070 Super | 1 | $0.121/hr |
| INT4 (quantized) | 2.3 GB | 2.8 GB | RTX 3060 | 1 | $0.088/hr |
How to run Wan2.2-TI2V-5B
Run Wan2.2-TI2V-5B with Diffusers (Python)
From Wan-AI/Wan2.2-TI2V-5B-Diffusers's own model card (requires diffusers installed from source as of this model's release).
import torch
from diffusers import WanPipeline, AutoencoderKLWan
from diffusers.utils import export_to_video
model_id = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
pipe.to("cuda")
output = pipe(prompt="a description of the scene", height=704, width=1280, num_frames=121).frames[0]
export_to_video(output, "ti2v_out.mp4", fps=24)Source: https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers/raw/main/README.md
Run Wan2.2-TI2V-5B with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled, and lib/pods/catalog.ts's comfyui-wan-video first-party pod uses this same checkpoint. Download Wan-AI/Wan2.2-TI2V-5B's checkpoint into the models folder and load it in a workflow.
Deploy Wan2.2-TI2V-5B on Aquanode
Aquanode has no one-click deploy template for Wan2.2-TI2V-5B; it comes with ComfyUI preinstalled, so you only need to load the checkpoint, not install anything. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch the ComfyUI template sized to the requirement above (1× RTX 6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch the ComfyUI template