WorkflowListedExternal

Stable Video Infinity 2 1080p 60 FPS ComfyUI Workflow for Wan 2.2 I2V by Smittie

Smittie's SVI2 1080p 60 FPS Workflow

Sourcecivitai.com/models/2288118

TaskMultiCapabilitiesImage to image · UpscalingFamilyWanEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Jul 18, 2026

Source description

Smittie's SVI2 1080p 60 FPS Workflow

Description

With this workflow you can generate a longer video in 1080p and 60 FPS without color or motion mismatch between the video segments (or choose cross-fade or jump-cut as transition) and inject anchor images (not end images) as further detailed guidance. You can also continue videos of ANY length (series, movies, etc.) without running into RAM issues.

If you just want to use I2V or continue videos that are only a few seconds long, then you can still use workflow v4. This one doesn't require the ComfyUI-Terminal node.

At least 16 GB of VRAM recommended, but with more quantized versions of the Wan 2.2 I2V diffusion models you can go even lower. This workflow was tested with 24 GB of VRAM and 64 GB of RAM.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

Use this ComfyUI workflow with Wan Video 2.2 I2V-A14B to turn input images or existing videos into longer 1080p video at 60 FPS, continue sequences across segments without color or motion mismatch, add anchor images for guidance, and choose cross-fade or jump-cut transitions.

Flow

The workflow includes nodes for loading images and videos, resizing and encoding inputs, sampling and interpolating frames, previewing results, and combining video.

Inputs and outputs

For image-to-video, provide an input image; for continuation, load a video and use anchor images rather than end images for added guidance.
The described output is longer 1080p video at 60 FPS, including continuations of any length such as series and movies.

Setup

Download the workflow from https://civitai.com/models/2288118 and follow its version-specific Initial Setup note before use.
Suggestion · not verified
If you only need image-to-video or a continuation lasting a few seconds, the listing describes workflow v4 as an alternative that does not require the ComfyUI-Terminal node.

Dependencies

The listed model files are DasiwaWAN22I2V14BLightspeed_tastysinHighV81.safetensors, DasiwaWAN22I2V14BLightspeed_tastysinLowV81.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, and wan_2.1_vae.safetensors.
The listed node packs and pins are comfyui_local_lora_gallery (1.1.4), comfyui-easy-use (1.3.6), comfyui-kjnodes (79f529a84a8c20fe5dcdfa984c6be7a94102c014), comfyui-videohelpersuite (8550981384301e9bc5bfea83e5c2c75258102593), and jovimetrix (2.1.25).

Configuration

Choose cross-fade or jump-cut between video segments.
Suggestion · not verified
Plan for at least 16 GB of VRAM; more-quantized Wan 2.2 I2V diffusion models may allow less.
Suggestion · not verified

Cautions

The listing does not state a license, so verify the applicable terms before use.
Suggestion · not verified
Before use, check that these two model files are present: DasiwaWAN22I2V14BLightspeed_tastysinHighV81.safetensors and DasiwaWAN22I2V14BLightspeed_tastysinLowV81.safetensors.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/2288118

Verified Jul 18

Source excerpts

1 excerpt

NoteJul 18civitai.com/models/2288118

Source context: 2336 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B