Text-to-Video
Diffusers
Safetensors
LTX2Pipeline
physisserve
ltx-2.5
autoregressive
video-generation
same-step-kv
Instructions to use Physis-AI/physisserve-ltx2p5_22b-same_step-ls-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Physis-AI/physisserve-ltx2p5_22b-same_step-ls-dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Physis-AI/physisserve-ltx2p5_22b-same_step-ls-dev", 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
Commit History
9 days ago
-
docs: add model card and PhysisServe logo
Verified signatureae632ea
13 days ago
-
Standard Diffusers layout: loadable by stock diffusers
Verified signature877fa76 -
Empty the README; drop files nothing loads
Verified signature6a8e351 -
Add files using upload-large-folder tool
Verified signature6b649d4 -
initial commit
Verified signature5ae8a0b