Instructions to use Hmrishav/t2v_sketch-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Hmrishav/t2v_sketch-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Hmrishav/t2v_sketch-lora", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
vram
#2
by deleted - opened
how much memory vram needs to work. I have installed it in a rtx 4080 32gb ram and 12 vram and always say me out of memory. I have run locally wan 2.1 in my pc without problem.
All experiments except for training the LoRA were performed on a 4090 with 24 GiB of vram. Maybe further quantization is needed from your end as modelscope t2v has fewer params then wan.