In this guide, we’ll walk through the full process of online training on TensorArt using Wan2.2. For this demo, we’ll be using image2video training so you can see direct results.

Step 1 – Open Online Training

Go to the Online Training page.
Here, you can choose between Text2Video or Image2Video.
👉 For this tutorial, we’ll select Image2Video.

Step 2 – Upload Training Data

Upload the materials you want to train on.

• You can upload them one by one.

• Or, if you’ve prepared everything locally, just zip the files and upload the package.

Step 3 – Adjust Parameters

Once the data is uploaded, you’ll see the parameter panel on the right.

💡 Tip: If you’re training with video clips, keep them around 5 seconds for the best results.

Step 4 – Set Prompts & Preview Frames

• The prompt field defines what kind of results you’ll see during and after training.

• As training progresses, you’ll see epoch previews. This helps you decide which version of the model looks best.

• For image-to-video LoRA training, you can also set the first frame of the preview video.

Step 5 – Start Training

Click Start Training once your setup is ready.
When training completes, each epoch will generate a preview video.

You can then review these previews and publish the epoch that delivers the best result.

Step 6 – Publish Your Model

After publishing, wait a few minutes and your Wan2.2 LoRA model will be ready to use.

Recommended Training Parameters (Balanced Quality)

Network Module: LoRA
Base Model: Wan2.2 – i2v-high-noise-a14b
Trigger words: (use a unique short tag, e.g. your_project_tag*)*

Image Processing Parameters

• Repeat: 1

• Epoch: 12

• Save Every N Epochs: 1–2

Video Processing Parameters

• Frame Samples: 16

• Target Frames: 20

Training Parameters

• Seed: –

• Clip Skip: –

• Text Encoder LR: 1e-5

• UNet LR: 8e-5 (lower than 1e-4 for more stability)

• LR Scheduler: cosine (warmup 100 steps if available)

• Optimizer: AdamW8bit

• Network Dim: 64

• Network Alpha: 32

• Gradient Accumulation Steps: 2 (use 1 if VRAM is limited)

Label Parameters

• Shuffle caption: –

• Keep n tokens: –

Advanced Parameters

• Noise offset: 0.025–0.03 (recommended 0.03)

• Multires noise discount: 0.1

• Multires noise iterations: 10

• conv_dim: –

• conv_alpha: –

• Batch Size: 1–2 (depending on VRAM)

• Video Length: 2

Sample Image Settings

• Sampler: euler

• Prompt (example):

Tips

• Keep training videos around ~5 seconds for best results.

• Use a consistent dataset (lighting, framing, style) to avoid drift.

• If previews show overfitting (blurry details, jitter), lower UNet LR to 6e-5 or reduce Epochs to 10.

• For stronger style binding: increase Network Dim → 96 and Alpha → 64, while lowering UNet LR → 6e-5.