import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("muhammad-taqi512/SLORA", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]SLORA: Advanced Text-to-Video Generator 🎬
SLORA is a state-of-the-art open-source text-to-video generation model built on a high-end diffusion architecture. Designed and engineered by Muhammad Taqi, SLORA mirrors the power, syntax pipelines, and performance standard of Wan-AI/Wan2.1-T2V-14B, delivering high-definition cinematic dynamics, brilliant text alignment, and fluid motion generation.
🌟 Key Features
- High-Fidelity Text-to-Video: Translates complex descriptive prompts into rich, vivid temporal video sequences.
- Wan2.1 Compatible Syntax: Built with standardized model routing, parameter configurations, and Diffusers integration identical to
Wan-AI/Wan2.1-T2V-14B. - Flexible Resolution Support: Optimized for both 480P and 720P high-performance generation.
- Advanced Spatiotemporal VAE: Incorporates seamless encoding and decoding architectures for ultra-smooth frame continuity.
💾 Installation & Setup
Ensure your environment has PyTorch installed along with the required huggingface ecosystem libraries.
# Clone the repository
git clone [https://huggingface.co/muhammad-taqi512/SLORA](https://huggingface.co/muhammad-taqi512/SLORA)
cd SLORA
# Install required dependencies
pip install -U diffusers transformers accelerate torch torchvision
- Downloads last month
- 58