Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
HSR Video LoRA - WAN2.1 T2V 1.3B
LoRA fine-tuned WAN2.1-T2V-1.3B for HSR robot manipulation video generation.
Training Details
- Base model: Wan-AI/Wan2.1-T2V-1.3B-Diffusers
- LoRA rank: 64, alpha: 64
- Training objective: Flow matching velocity prediction
- Training videos: 638 HSR robot episodes
- Epochs: 30, Final loss: 0.2015
- Target modules: to_q, to_k, to_v, to_out.0
Usage
from diffusers import WanPipeline
from peft import PeftModel
pipe = WanPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, "FT-LLM-2026-RAMEN/hsr-video-lora-wan21")
Project
ICRA 2026 RAMEN - DreamGen-inspired synthetic trajectory generation pipeline.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for FT-LLM-2026-RAMEN/hsr-video-lora-wan21
Base model
Wan-AI/Wan2.1-T2V-1.3B-Diffusers