Aller au contenu
WorkflowPrésentéExterne
Télécharger

🍥 Wan 2.2 (GGUF) [i2v / FFLF] + [t2v] Workflow — 🟢v1.1

Fix Manual Scale - previously not scaling to the right resolution in megapixel for certain aspect ratio

Sourcecivitai.com/models/2170698
TâcheMultipleCapacitésImage en image · Mise à l'échelleFamilleWanVersionEstimé VRAMNot yet characterizedUnratedClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Version
LF Calculate Megapixel V1.json
Source
Civitai
Mis Ă  jour
3 nov. 2026

Description de la source

20/12/25

Fix Manual Scale - previously not scaling to the right resolution in megapixel for certain aspect ratio

Fix Non-GGUF Workflows Default Model in Loader - previously accidentally swap i2v - t2v low models, causing i2v to generate different video from image used.

Changed Video Upload format in Video Merger and Post Processing workflow from "Wan" to "AnimateDiff" - which will cause missing frames if frames are trimmed off.

Added Volume Adjust to MMAudio subgraphs

All workflows will be included in one download files.

What you need

Hardware and download-size estimates are not available yet.

Exigences

Packs de nœuds

2

  • comfyui-kjnodes

    Non résolu

    Pack de nœud · Registry

  • rgthree-comfy

    Non résolu

    Pack de nœud · Registry

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Objectif

  • This ComfyUI workflow generates videos from text prompts, a single image, or two images in t2v, i2v, or FFLF mode, with generated videos available for preview and post-processing.

Flux

  • Choose a mode, add the needed images, enter prompts or LoRAs, set resolution, duration, and steps, then run the workflow.

  • Included utilities cover video post-processing, video merging or joining, and simple megapixel calculation.

Entrées et sorties

  • The i2v-only batch option accepts images from a folder and supports different dimensions or aspect ratios.

  • Post-processing can interpolate frames, upscale with a model, trim frames, adjust speed or FPS, sharpen, add a logo or watermark, save the last frame, and select frames; generated videos go to ComfyUI/Output.

Installation

  • Use ComfyUI's Custom Node Manager to install missing custom nodes, select all, and restart ComfyUI; manually search for ComfyUI-GGUF if it is not listed.

    Suggestion · non vérifié

DĂ©pendances

  • The workflow requires 9 custom node packs, or 10 when using MMAudio.

  • The listed packs are ComfyUI-GGUF, rgthree-comfy, ComfyUI-East-Use, ComfyUI-KJNodes, ComfyUI-VideoHelpSuite, ComfyUI-essentials, ComfyUI-Frame-Interpolation, ComfyUI-mxToolkit, WhiteRabbit, and ComfyUI-MMAudio for workflows that use it.

  • The included workflow data specifies rgthree-comfy 1.0.2511111955 and ComfyUI-KJNodes 1.1.9.

Configuration

  • Available controls include prompts, LoRAs, duration, resolution, seed, manual image scaling, total and split steps, FPS, interpolation, upscaling, trimming, sharpening, and watermarks.

  • The usage notes suggest pairing 4 total steps with 2 split steps, 6 with 3, or 8 with 4.

    Suggestion · non vérifié

  • For lower VRAM, choose lowvram in ComfyUI Settings > Server-Config > Memory > VRAM management mode, then restart ComfyUI.

    Suggestion · non vérifié

Précautions

  • Only ComfyUI Desktop is listed as tested; ComfyUI-Swwan has been reported to conflict with workflow switches, and the notes say to disable Node 2.0 on the latest ComfyUI.

  • For i2v batch generation, set all post-processing options before starting because they cannot be changed afterward.

    Suggestion · non vérifié

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipalVersion 2520066
civitai.com/models/2170698

Vérifié 3 nov.

Workflow instructions

Author notes from 4 - Utilities Workflow/LF Calculate Megapixel V1.json · selected release

[📥Models Download Link + 📖Detailed Guide (CivitAI Article)](https://civitai.com/articles/22850) [📒Workflow (CivitAI)](https://civitai.com/models/2170698) [🍥Lannfield (CivitAI)](https://civitai.com/user/Lannfield)

Download files

Artefacts du modèle

2 artefacts

Wan22GGUFI2vFFLFT2v_V11.zip

zip · 363 KB · SHA-256 e5a9eb89f4a4…7909 · Civitai

Download file

LF Calculate Megapixel V1.json

json · 6,24 KB · SHA-256 c06e9bb46a23…2da2

Download file

Extraits de sources

3 extraits
Note3 nov.civitai.com/models/2170698

Source context: 8661 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note2 oct.civitai.com/models/2170698

Source context: 8378 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note19 juil.civitai.com/models/2170698

Source context: 7677 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B