First Wan 2.2 5B image-to-video task: verify the input through to the saved clip

File and download boundary: ComfyUI World provides source references and metadata only. Model and LoRA weights, node packages, and workflow files stay with their original providers; this site does not store, mirror, or proxy them. Downloads and access conditions are controlled by each provider.

Purpose and scope

This guide follows the 5B TI2V image-input path specifically. The model-family reference explains alternatives; this page handles input, execution stages and output verification.

Source-supported context

The official 5B example lists separate diffusion, UMT5 and Wan 2.2 VAE resources and distinguishes 14B routes. The file table records documentation, not a scan of your environment. Source 1 Source 2

Before you start

1. Confirm the author's core/template requirements and permission to use the input image. Check that your ComfyUI build includes the example's core nodes; the official guide says some may not yet be in the latest stable release.

2. Prepare the three 5B resources rather than substituting a 14B VAE or dual-stage graph.

3. Begin with one task at the selected template's supported dimensions and frame count; use a smaller load only if that workflow and model permit it.

Steps and checks

The sequence below is an editorial procedure based on the cited context, not a diagnosis already confirmed for your environment.

Step 1. Obtain the 5B TI2V example from the official page/template library, preserve the graph and check all three loader selections.

Step 2. Enable the example's image path, load your image and inspect crop/resize and dimensions rather than only editing the prompt on a text-only branch.

Step 3. Run a simple motion prompt and observe model loading, sampling, VAE decoding and video saving separately.

Step 4. Check playback, resolution, frames and duration; if the workflow supports it, adjust one load factor at a time while recording environment conditions.

Completion check

The image actually reaches the image-to-video branch and the complete video is saved. Sampling at 100% does not prove decoding and export completed.

Limitations and cautions

No video was generated here and no guaranteed 8GB/24GB capacity or speed is asserted. Obtain the original JSON upstream; it is not copied into this pack.

Files named by the source documentation

These are the selected documentation example's declarations, not inspected local files or direct downloads. No weights or checksum results are included; verify the revision for your task.

File	Directory category	Documented source
wan2.2_ti2v_5B_fp16.safetensors	diffusion_models	Source
umt5_xxl_fp8_e4m3fn_scaled.safetensors	text_encoders	Source
wan2.2_vae.safetensors	vae	Source

Original sources

• Wan2.2 native workflows — original record checked 2026-09-21.
• ComfyUI Server API routes — original record checked 2026-09-21.

Localization prepared: 2026-09-22. The source-check dates above were inherited from the existing article; this translation does not claim they were all rechecked today. No GPU run, minimum-memory measurement or runtime guarantee is supplied.

Related troubleshooting and guides

• Wan 2.2 5B versus 14B: match the task, model stages and VAE
• VAE out of memory after sampling finishes: diagnose decoding separately
• Video export fails or plays incorrectly: check frames, encoding and audio separately