Sponsored by
Designkit Free Background Remover
Remade-AI / Inflate
Model's Last Updated: 5월 26 2025
image-to-video
Introduction of Inflate
Model Details of Inflate
Inflate Effect LoRA for Wan2.1 14B I2V 480p
Overview
This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to inflate any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!
Features
- Transform any image into a video of it being inflated
- Trained on the Wan2.1 14B 480p I2V base model
- Consistent results across different object types
- Simple prompt structure that's easy to adapt
Community
- Discord: Join our community to generate videos with this LoRA for free
- Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
- Prompt
- The large, bald man rides a gray donkey, then infl4t3 inflates it, both the man and the donkey expanding into giant, inflated figures against the desert landscape.
- Prompt
- The stylish woman in a white pantsuit smiles, then infl4t3 inflates it, her form expanding, and her suit balloons around her in a chic, air-filled design.
- Prompt
- The young boy riding a bicycle down the dirt road is surprised, then infl4t3 inflates it, his body and bike inflating together like a whimsical, cartoonish balloon.
- Prompt
- The red apple sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.
Model File and Inference Workflow
📥 Download Links:
- inflate_20_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:
infl4t3 inflates it
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 30 seconds of video comprised of 9 short clips (each clip captioned separately) of things being inflated
- Epochs: 20
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!
Runs of Remade-AI Inflate on huggingface.co
349
Total runs
0
24-hour runs
0
3-day runs
67
7-day runs
-84
30-day runs
More Information About Inflate huggingface.co Model
Url of Inflate
Inflate huggingface.co Url
Provider of Inflate huggingface.co
Other API from Remade-AI
Total runs:
395
Run Growth:
356
Growth Rate:
90.13%
Total runs:
212
Run Growth:
138
Growth Rate:
65.09%