license: apache-2.0 language:

• en base_model:
• Wan-AI/Wan2.1-I2V-14B-480P
• Wan-AI/Wan2.1-I2V-14B-480P-Diffusers pipeline_tag: image-to-video tags:
• text-to-image
• lora
• diffusers
• template:diffusion-lora
• image-to-video widget:
• text: >- A man with short hair and a beard clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. output: url: example_videos/super1.mp4
• text: >- A South Asian man with dark hair and a beard clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. output: url: example_videos/super2.mp4
• text: >- An old Asian man with short hair clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. output: url: example_videos/super3.mp4
• text: >- A man with curly dark hair and a beard clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. output: url: example_videos/super4.mp4

Model File and Inference Workflow

📥 Download Links:

• super_saiyan_35_epochs.safetensors - LoRA Model File
• wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

---

Recommended Settings

• LoRA Strength: 1.0
• Embedded Guidance Scale: 6.0
• Flow Shift: 5.0

Trigger Words

The key trigger phrase is: 5up3r super saiyan transformation

Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work very well.

ComfyUI Workflow

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

See the Downloads section above for the modified workflow.

Model Information

The model weights are available in Safetensors format. See the Downloads section above.

Training Details

• Base Model: Wan2.1 14B I2V 480p
• Training Data: Trained on 1 minute of video comprised of 13 short clips (each clip captioned separately) of various Super Saiyan transformations
• Epochs: 35

Additional Information

Training was done using Diffusion Pipe for Training

Acknowledgments

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!