NOTICE ~Make sure to download the correct version for the tool you use 😉~ NOTICE

Wan LCM

Some other versions of this have been uploaded, however the internal structure of those prevented me from using them with Blissful Tuner (My advanced, extended Musubi Tuner: https://github.com/Sarania/blissful-tuner/ ). This is a Rank 16 extraction of https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill for use with LCM schedulers to allow high quality 4 to 8 step diffusions with Wan architecture models. Both a Blissful compatible version and Comfy compatible version are provided. These are also Rank 16 and finely targeted to provide better compatibility with other LoRA!

Instructions for use:
For Blissful Tuner, you need to provide "--sample_solver lcm" and set "--guidance_scale 1.0" - this means no negative prompt. However in exchange you get exceptional quality, quick video diffusions with pretty much any Wan arch model - I've tried it with T2V, I2V, and Skyreels V2 myself and it works perfectly all around! It also works with other LoRA that I've tried - the kissy showcase video here was made with my AmorousLesbianKisses model and the four wheeler video was made with https://civitai.com/models/1698719/high-speed-dynamic?modelVersionId=1922492 ! To offset the lack of CFG/negative prompt, you do have "--prompt_weighting" available. Also I've had luck using CFG on just the first step with a low value like 1.6 if you REALLY need that negative (e.g. "--cfg_schedule 1:1.6" ). Additionally a "--flow_shift" of 8.0 is recommended!

For Comfy, it's basically the same thing you need an LCM sampler, guidance/cfg = 1.0, flow_shift=8.0 and just load the LoRA like any other! I tested it in Kijai's WanVideoWrapper and it works beautifully!

I like to use 6 steps for T2V and 4 for I2V. Showcase videos (832x1104@81f) were made in about 5 minutes on my 4070 Ti Super and then they were VFI'd from 16 fps to 32fps in another couple minutes. Please note that I did not train the distilled model, credit for that goes to lightx2v - thanks to them for releasing their model under permissive terms! I've been waiting for a distilled Wan that was up to my quality standards and this is it. IMO it's superior to others such as CausVid/AccVid. As mentioned above I've had success not only with T2V, but also I2V and even Skyreels V2! As such it's likely most any Wan derived model would be compatible.

Please note that as mentioned, versions of this have been uploaded before. However, I felt it was still worth posting these due to the compatibility issues mentioned above, and also my extraction is smaller and more targeted for better compatibility with other LoRA.

P.S. If you want to extract your own LoRA from Wan or other diffusion models, the script I used is one of the many extras in Blissful Tuner https://github.com/Sarania/blissful-tuner/blob/main/src/blissful_tuner/extract_lora.py