Wan 2.1 Lightspeed

Generates Wan 2.1 videos in a fraction of time.

Recommended settings:

• Sampler: LCM (Sheduler: simple or LTX)

• Steps: 4

• CFG: 1

• Sigma-Shift 5

Original Model from Lightx2v converted to FP8 quantisation.

☠️ Do not use any extra speed-up tricks or LoRAs or it may mess up your generations ... 🤬

⚠️ Hint: Most of the time the model is taking you by word. If you write "white" it is white. "Translucent" is translucent... like for the fluids. 💦 Now you know! 🫵 translucent whitish 🤫

⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬇️

Sage Attention, Flash Attention, Radial Attention, q8-kernel, sgl-kernel, vllm are built in, no need to enable it!

Recommended specs:

8 GB VRAM, 32 GB RAM

Sample times: <2 minutes for 81 frames, 4 steps on RTX 4070 Ti Super.

Compatible with 14B LoRAs.

I normally use 0-2 LoRAs, strength at 0.4-1 depending on how much the effect should be. 0.7-0.9 works best most of the time, not overwriting the style of an image.
At multiple LoRAs is seems best to tune the strength a bit down to 0.3-0.6.

Basic workflow example:

Here: https://civitai.com/models/1811161?modelVersionId=2049602

My favourite UI:

SwarmUI https://github.com/mcmonkeyprojects/SwarmUI

Testing (my specs):

I can go wild on setting with this full checkpoint, even with added LoRAs:

• 121 frames possible: ~ 3 minutes

• 121 frames on 24 fps possible (more motion): ~ 3 minutes

• 128 frames on 24 fps possible (more motion and extended): ~ 3.5 minutes

If needed:
Clip/T5-Encoder: umt5_xxl_fp8_e4m3fn_scaled.safetensors