modelle/Wan 2.2 Lightning LoRAs - i2v-seko-v1-high-r64

Wan 2.2 Lightning LoRAs - i2v-seko-v1-high-r64

|
12/22/2025
|
10:55:42 PM
| Discussion|
0

Empfohlene Prompts

<base> <lora:Wan2.2-Lightning_T2V-A14B-4steps-lora_HIGH_fp16> <refiner> <lora:Wan2.2-Lightning_T2V-A14B-4steps-lora_LOW_fp16>,<video> <lora:...i2v-high> <videoswap> <lora:...i2v-low>

Empfohlene Parameter

samplers

LCM

steps

4

cfg

1

resolution

480x832, 832x480, 720x1280, 1280x720

Tipps

Use 1 strength on both LoRAs with 2+2 steps and switch at step 2 (50%).

Apply Sigma Shift value of 5.

Be very descriptive in prompts, as short prompts tend to yield more random outcomes.

Optimal generation times are less than 3 minutes.

Previous usage tip: 0.125 strength on both LoRAs with 4 steps and switch at 2.

Currently testing optimal settings for ComfyUI and SwarmUI.

EXPERIMENTAL!

Extreme speed-up of Wan 2.2 T2V and I2V with just 4 steps

https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/

Update: 25/08/08

  • The I2V Lora-Upload seem to be broken, re-uploaded it again

  • Changed some Usage descriptions

  • Mentioned scheduler/sampler combo

Update: 25/08/07

  • Added I2V LoRAs

Update: 25/08/05

  • Added more Infos and LoRAs fix1

Usage

SwarmUI

  1. CFG: 1

  2. Steps: 4

  • For T2V Use with this at the end of your prompt: <base> <lora:Wan2.2-Lightning_T2V-A14B-4steps-lora_HIGH_fp16> <refiner> <lora:Wan2.2-Lightning_T2V-A14B-4steps-lora_LOW_fp16> (adapt the lora filenames to whatever specific filenames you have locally)

  • For I2V, use <video> <lora:...i2v-high> <videoswap> <lora:...i2v-low> and of course use the i2v loras

  • the I2V Lightning LoRA appears to target 16 fps

General:

  • 1 strength on both

  • 2+2 steps (total 4)

  • switch at 2 (50%)

  • Sigma Shift: 5

  • Sampler: LCM

  • Scheduler: LTX

  • You need to be very descriptive, short prompts leading to much more random things.

  • work best at 81x480x832, 81x832x480, 81x720x1280, 81x1280x720

usage tip first loras (outdated):

  • 0.125 strength on both

  • 4 steps

  • switch at 2

Did not figured out optimal settings for comfyui or swarmui ... still testing. Let me know! :)

Generation times <3 minutes

Zurück
Raz's Unstable Artistic Takes - GlitchStorm - Mk.1
Weiter
Oops! All Toons - Illustrious v1.0 - Illustrious_v1.0

Modell-Details

Modelltyp

LORA

Basismodell

Wan Video 2.2 I2V-A14B

Modellversion

i2v-seko-v1-high-r64

Modell-Hash

d176c808d6

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Bilder von Wan 2.2 Lightning LoRAs - i2v-seko-v1-high-r64

Bilder mit Werkzeug

A furry humanoid character with a backpack and axe walking through a post-apocalyptic landscape. This is an AI generated image using Stable Diffusion.