fal-ai/wan-22-trainer/i2v-a14b
Train custom LoRAs for Wan-2.2 T2V/I2V 480P
Training
Commercial use
Input
or
Hint: Drag and drop files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Additional Settings
Customize your input with more control.
Your request will cost $0.005 per step (minimum of 100 steps is charged). For $5 you can fine-tune a LoRA for 1000 steps.
Training history
Nothing here yet...
Fine-tune your training parameters and start right now.
Note: these are the most recent training requests. For the full history, check the requests tab.
Trains a LoRA for the Wan 2.2 I2V-A14B model (`image + text prompt` → `video`).
The training dataset must contain at least one video — image-only datasets are rejected with an error.
If a mix of images and videos is provided, only the videos are used for training; images are ignored.
Use this endpoint only if you intend to use the LoRA with the I2V inference model.