Instructions to use optimum-intel-internal-testing/tiny-random-ltx2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use optimum-intel-internal-testing/tiny-random-ltx2.5 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("optimum-intel-internal-testing/tiny-random-ltx2.5", 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
3 days ago
-
Add reference OpenVINO IRs
Generated with: - transformers==5.15.1 - optimum-intel==2.3.0.dev0+8c40189b - openvino==2026.5.0-23697 (#1) - Add reference OpenVINO IRs (de46413019f5b86ba4d87ef7d1e5df543bc25377)524a4f3
-
Add duration_head, prompt_enhancer and processor (LTX-2.5-only components)
Verified signature3f43040
-
Rebuild fixture with diffusers 0.40.0 (ff_bias, use_keyframes_abs_pos_embedding, use_prompt_adaln_single) for architecture fidelity with real LTX-2.5
Verified signature5e56afb -
Add tiny random LTX-2.5 model fixture
Verified signature9e88871 -
initial commit
Verified signaturec067f8a