Instructions to use ltx-community/LTX-2.3-Transformer-GroupB-sm120-cu130-r0e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ltx-community/LTX-2.3-Transformer-GroupB-sm120-cu130-r0e with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ltx-community/LTX-2.3-Transformer-GroupB-sm120-cu130-r0e", 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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -49,3 +49,16 @@ def generate(*args, **kwargs):
|
|
| 49 |
```
|
| 50 |
|
| 51 |
Public repo (graph only) → no token needed. Built with the job in this repo's `job.py`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
```
|
| 50 |
|
| 51 |
Public repo (graph only) → no token needed. Built with the job in this repo's `job.py`.
|
| 52 |
+
|
| 53 |
+
## How to reproduce or customize
|
| 54 |
+
This repo bundles the `job.py` that built it. To rebuild (or retarget to another GPU arch / base model), download it and run on HF Jobs:
|
| 55 |
+
```bash
|
| 56 |
+
hf jobs uv run job.py \
|
| 57 |
+
--flavor rtx-pro-6000 \
|
| 58 |
+
--image pytorch/pytorch:2.9.1-cuda13.0-cudnn9-devel \
|
| 59 |
+
--secrets HF_TOKEN
|
| 60 |
+
```
|
| 61 |
+
Customize the output repo name with `OUTPUT_REPO_BASE_NAME` / `OUTPUT_REPO_ID`, and set `LTX_GROUP_B=1` (this build adds the in-context self-attention mask). The exact build environment (torch 2.12.0+cu130, etc.) is recorded in `environment.json`.
|
| 62 |
+
|
| 63 |
+
## Job run
|
| 64 |
+
- [linoyts/6a3270a3fb114ff24a388567](https://huggingface.co/jobs/linoyts/6a3270a3fb114ff24a388567)
|