Downloads · 30 days
0
wan2.1-robotwin-lora-sft
cjgogo/wan2.1-robotwin-lora-sft
wan2.1-robotwin-lora-sft is a machine learning model from cjgogo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Fine-tuned from Wan2.1-I2V-14B-480P using VideoX-Fun framework on RoboTwin dataset.
Access
Public
Updated May 9, 2026
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- May 9, 2026
- Updated
- May 9, 2026
- SHA
- 2ab8e092
Base models
Model card
From the Hugging Face model README
Wan2.1 LoRA SFT for Robot Video Generation
Fine-tuned from Wan2.1-I2V-14B-480P using VideoX-Fun framework on RoboTwin dataset.
Part of the WorldArena World Model Challenge.
Training Details
| Parameter | Value |
|---|---|
| Framework | VideoX-Fun |
| Base Model | Wan2.1-I2V-14B-480P |
| Training Data | RoboTwin aloha-agilex_clean_50 (2,500 videos, 50 tasks) |
| LoRA Rank | 32 |
| LoRA Alpha | 16 |
| LoRA Targets | q, k, v, ffn.0, ffn.2 |
| Learning Rate | 1e-4 (constant with warmup) |
| Warmup Steps | 100 |
| Precision | bf16 |
| Resolution | 640 × 640 |
| Frames | 81 per video |
| Batch Size | 1 per GPU (2 GPUs) |
| Total Steps | 12,500 (planned), 2,200 (completed) |
Checkpoints Available
| File | Training Steps | Description |
|---|---|---|
| checkpoint-1200.safetensors | 1,200 | ~1 epoch of training |
| checkpoint-2200.safetensors | 2,200 | Latest checkpoint, used for 1000-video inference |
Each checkpoint has a ComfyUI-compatible version.
Usage
Inference with VideoX-Fun:
Evaluation Results (WorldArena Track 1, 10 samples)
| Metric | Baseline Wan2.1 | SFT-Wan2.1 (ckpt300) |
|---|---|---|
| Image Quality | 70.44 | 48.80 |
| Background Consistency | 69.58 | 90.40 |
| Subject Consistency | 59.90 | 82.33 |
| Flow Score | 16.18 | 21.29 |
SFT-Wan2.1 shows significant improvements in background consistency (+20.8), subject consistency (+22.4), and flow score (+5.1).
Limitations
- Intended for research on robot video world models
- May fail on long-horizon manipulation and complex physical contact
- Instruction following accuracy still limited (~54%)
- Full 1,000-video WorldArena evaluation in progress
- Library
- peft
- License
- apache-2.0
- Created
- May 9, 2026
- Updated
- May 9, 2026