Samurai Transformation (Wan2.1 I2V LoRA)

Request a Wan2.1 LoRA on our Discord and we will train and open-source it for free.

Join our Discord to generate videos of the Samurai Transformation LoRA for free.

Wan2.1 14B I2V 480p v1.0:

Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people undergoing a samurai transformation. This was trained on the Wan.21 14B I2V 480p model.

The trigger word is: '54mur41 samurai transformation'

See below for some prompt examples that worked well for me. You can also check the videos I've posted here for the captions that were used to generate them. For each video the input image is just the first frame.

Recommended Settings:

LoRA strength = 1.0

Embedded guidance scale = 6.0

Flow shift = 5.0

Here's a link to the Wan2.1 I2V LoRA inference workflow I used to generate these videos: is a slight modification to Kijai's version, with the main difference being the addition of the WanVideo Lora Select node, connected to the 'lora' field of the WanVideo Lora Select node. Find Kijai's original workflow here:
/>

Check out all our LoRAs on our page: Examples:

The weary frog's eyes widen as the background subtly shifts to a blurry, animated rain-soaked street, transforming into a 54mur41 samurai frog warrior, now holding a tiny katana, with a determined gaze.

The video begins with purple Thanos from Marvel. Thanos begins the 54mur41 samurai transformation, and becomes a samurai. Thanos is wearing a traditional samurai outfit, and is holding a katana. The background behind Thanos is a misty mountainous landscape.

The video begins with a rabbit. The rabbit begins the 54mur41 samurai transformation, and becomes a samurai. The rabbit is wearing a traditional samurai outfit, and is holding a katana. The background behind the rabbit is a misty mountainous landscape.

Let me know if there are any questions, I'll be happy to help!