Skip to content
WorkflowListedExternal
Open source

Wan 2.2 - FFLF - XT 404 - Master UI

V.1.0

TaskImage to videoFamilyWanVersionRelease 2538057 — I2V - X-T - FFLF.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
I2V - X-T - FFLF.json
Source
Civitai
Updated
Oct 18, 2026

What you need

Model files
26.6 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

5

Node packs

5

AI-generated commentary

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

Purpose

  • Wan 2.2 - FFLF - XT 404 - Master UI is a ComfyUI workflow for Wan Video 2.2 I2V-A14B that uses text and image inputs to generate video frames, can interpolate between start_image and end_image, and routes decoded frames toward video encoding.

Flow

  • The described path loads a model and VAE, caches text and vision inputs, runs WanImageToVideoUltra and XT-404 Skynet 1, refines with XT-404 Skynet 3, and decodes with VAE Decode.

  • Decoded frames can pass through Temporal Lock Pro, OLED Dynamix, Organic Skin, and Wan Chroma Mimic before Video Combine and Wan Compressor.

Inputs and outputs

  • Use a text prompt and image input; the T-X Interpolator uses start_image as the origin frame and end_image as the target frame.

  • The workflow produces decoded frames, with Video Combine and Wan Compressor listed for video encoding.

Setup

  • Use ComfyUI with Wan 2.2 VAE, CLIP, and UNet/Transformer models; Python 3.10+ is listed.

  • FFmpeg is listed for the Compressor node, and the installation notes specify imageio-ffmpeg and scikit-image.

Dependencies

  • The listed node packs are ComfyLiterals, comfyui-kjnodes, comfyui-videohelpersuite, ComfyUI-WanVideoWrapper, and crt-nodes.

  • The listed model files are clip_vision_h.safetensors, exitiumVICTRIX_highEXITIUMVICTRIX.safetensors, exitiumVICTRIX_lowEXITIUMVICTRIX.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, and wan_2.1_vae.safetensors.

Configuration

  • The described sequence places XT-404 Skynet 3 after XT-404 Skynet 1 with Denoise 0.3, then runs Temporal Lock Pro, OLED Dynamix, Organic Skin, and Wan Chroma Mimic.

  • Wan Chroma Mimic requires reference_image; the listed values are effect_intensity 0.25, oled_contrast 0.00, skin_metal_smooth 0.25, and detail_crispness 0.2.

  • For the T-X Interpolator, motion_amp amplifies motion vectors between keyframes, and detail_boost sharpens before VAE compression.

Cautions

  • If you plan to use GGUF quantized models, verify that ComfyUI-GGUF is available; without it, Cyberdyne Model Hub operates in Safetensors-only mode.

    Suggestion · not verified

  • The listed file wan_2.1_vae.safetensors is identified as a VAE, while the setup notes call for Wan 2.2 model components; verify which VAE your configuration should use.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2538057
civitai.com/models/2254670

Verified Oct 18

Source excerpts

3 excerpts

Source context: 295 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Source context: 282 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Source context: 233 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B