EasyWan22 FastMix

2025/08/25 FirstStepCfgHack
Boost1stStep sample: A-ON,
A-OFF |
B-ON,
B-OFF

----

Wan22-I2V-FastMix_v10

Wan 2.2 I2V-A14B, 6steps/generation. apache-2.0.
I'm using Q4KM with Geforce RTX 3060 12GB.

Wan22-I2V-FastMix_v10-H

• wan2.2i2vhighnoise14Bfp16.safetensors
• Wan2.2-Lightning/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/highnoise_model.safetensors

HighNoise

• Sampler

- scheduler: lcm - shift: 5 - cfg: 1 - sigmas: 1, 0.94, 0.85, 0.73, 0.55, 0.28, 0 - steps: 6, startstep: 0, endstep: 3

• Enhance-A-Video

- weight: 1

• Fresca

- use_fresca: true

• NAG

- Kijai default - Additional Negative Prompt: mouth moving, 嘴在动, talking, 说话, speaking, 讲话,

• EnhanceMotion: Wan2.2-Lightning/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/highnoise_model.safetensors: -1 ~ 1>

Wan22-I2V-FastMix_v10-L

• wan2.2i2vlownoise14Bfp16.safetensors
• lightx2v14BT2Vcfgstepdistillloraadaptiverankquantile0.15bf16.safetensors
• lightx2vI2V14B480pcfgstepdistillrank256bf16.safetensors

LowNoise

Generation

• Sampler

- scheduler: lcm - shift: 5 - cfg: 1 - sigmas: 1, 0.94, 0.85, 0.73, 0.55, 0.28, 0 - steps: 6, start_step: 3

• Enhance-A-Video

- weight: 1

• NAG

- Kijai default - Additional Negative Prompt: mouth moving, 嘴在动, talking, 说话, speaking, 讲话,

Refiner

SeedGacha SSR Video > Upscale x1.5 & Encode samples

• Sampler

- scheduler: lcm - shift: 5 - cfg: 1 - sigmas: 1.0, 0.97, 0.94, 0.90, 0.85, 0.795, 0.73, 0.65, 0.55, 0.42, 0.28, 0.14, 0.0 - steps: 12, start_step: 10 - addnoiseto_samples: true

• Enhance-A-Video

- weight: 1

• NAG

- Kijai default - Additional Negative Prompt: mouth moving, 嘴在动, talking, 说话, speaking, 讲话,