Instructions to use PrunaAI/PrunaVAED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use PrunaAI/PrunaVAED with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("PrunaAI/PrunaVAED", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - LTX.io
How to use PrunaAI/PrunaVAED with LTX.io:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download PrunaAI/PrunaVAED --local-dir models/PrunaVAED hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Fast pipeline (distilled model, no distilled LoRA needed) uv run python -m ltx_pipelines.distilled \ --distilled-checkpoint-path models/PrunaVAED/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/PrunaVAED/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# HQ pipeline (two-stage, higher quality) uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path models/PrunaVAED/<checkpoint>.safetensors \ --distilled-lora models/PrunaVAED/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/PrunaVAED/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -64,24 +64,24 @@ Both columns decode the same LTX-2.3 latent from the distilled pipeline.
|
|
| 64 |
<tr>
|
| 65 |
<td>
|
| 66 |
<video controls autoplay muted loop playsinline
|
| 67 |
-
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 68 |
</video>
|
| 69 |
</td>
|
| 70 |
<td>
|
| 71 |
<video controls autoplay muted loop playsinline
|
| 72 |
-
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 73 |
</video>
|
| 74 |
</td>
|
| 75 |
</tr>
|
| 76 |
<tr>
|
| 77 |
<td>
|
| 78 |
<video controls autoplay muted loop playsinline
|
| 79 |
-
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 80 |
</video>
|
| 81 |
</td>
|
| 82 |
<td>
|
| 83 |
<video controls autoplay muted loop playsinline
|
| 84 |
-
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 85 |
</video>
|
| 86 |
</td>
|
| 87 |
</tr>
|
|
@@ -98,20 +98,20 @@ Both columns decode the same LTX-2.3 latent from the distilled pipeline.
|
|
| 98 |
<th align="center">⚡ PrunaVAED</th>
|
| 99 |
</tr>
|
| 100 |
<tr>
|
| 101 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 102 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 103 |
</tr>
|
| 104 |
<tr>
|
| 105 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 106 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 107 |
</tr>
|
| 108 |
<tr>
|
| 109 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 110 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 111 |
</tr>
|
| 112 |
<tr>
|
| 113 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 114 |
-
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/
|
| 115 |
</tr>
|
| 116 |
</table>
|
| 117 |
|
|
@@ -146,7 +146,7 @@ differences (temporal consistency).
|
|
| 146 |
|
| 147 |
## Quickstart
|
| 148 |
|
| 149 |
-
End-to-end smoke
|
| 150 |
**distilled** two-stage pipeline, then decode the same latent with the stock
|
| 151 |
LTX-2.3 VAE and with PrunaVAED. Writes two mp4s and prints decode time (ms).
|
| 152 |
Needs a **CUDA GPU**.
|
|
@@ -162,12 +162,12 @@ cd PrunaVAED
|
|
| 162 |
# 3. Install dependencies
|
| 163 |
pip install -r requirements-test.txt
|
| 164 |
|
| 165 |
-
# 4. Run the
|
| 166 |
python demo/demo_distilled_decode.py
|
| 167 |
```
|
| 168 |
|
| 169 |
-
Outputs land in `outputs/
|
| 170 |
-
Edit `PROMPT` / resolution at the top of `
|
| 171 |
|
| 172 |
|
| 173 |
## Architecture
|
|
|
|
| 64 |
<tr>
|
| 65 |
<td>
|
| 66 |
<video controls autoplay muted loop playsinline
|
| 67 |
+
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/Ltx23VAED/04MhZs7YN08-Scene-0048.mp4">
|
| 68 |
</video>
|
| 69 |
</td>
|
| 70 |
<td>
|
| 71 |
<video controls autoplay muted loop playsinline
|
| 72 |
+
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/PrunaVAED/04MhZs7YN08-Scene-0048.mp4">
|
| 73 |
</video>
|
| 74 |
</td>
|
| 75 |
</tr>
|
| 76 |
<tr>
|
| 77 |
<td>
|
| 78 |
<video controls autoplay muted loop playsinline
|
| 79 |
+
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/Ltx23VAED/FAfMSWi0FSA-Scene-0200.mp4">
|
| 80 |
</video>
|
| 81 |
</td>
|
| 82 |
<td>
|
| 83 |
<video controls autoplay muted loop playsinline
|
| 84 |
+
src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/PrunaVAED/FAfMSWi0FSA-Scene-0200.mp4">
|
| 85 |
</video>
|
| 86 |
</td>
|
| 87 |
</tr>
|
|
|
|
| 98 |
<th align="center">⚡ PrunaVAED</th>
|
| 99 |
</tr>
|
| 100 |
<tr>
|
| 101 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/Ltx23VAED/8YSha7iU2ZI-Scene-1025.mp4"></video></td>
|
| 102 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/PrunaVAED/8YSha7iU2ZI-Scene-1025.mp4"></video></td>
|
| 103 |
</tr>
|
| 104 |
<tr>
|
| 105 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/Ltx23VAED/DZt-RtpcJZQ-Scene-0043.mp4"></video></td>
|
| 106 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/PrunaVAED/DZt-RtpcJZQ-Scene-0043.mp4"></video></td>
|
| 107 |
</tr>
|
| 108 |
<tr>
|
| 109 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/Ltx23VAED/9GDE5-rOOfk-Scene-0010.mp4"></video></td>
|
| 110 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/PrunaVAED/9GDE5-rOOfk-Scene-0010.mp4"></video></td>
|
| 111 |
</tr>
|
| 112 |
<tr>
|
| 113 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/Ltx23VAED/7y57zc-GvBA-Scene-0009.mp4"></video></td>
|
| 114 |
+
<td><video controls autoplay muted loop playsinline src="https://huggingface.co/PrunaAI/PrunaVAED/resolve/main/example/PrunaVAED/7y57zc-GvBA-Scene-0009.mp4"></video></td>
|
| 115 |
</tr>
|
| 116 |
</table>
|
| 117 |
|
|
|
|
| 146 |
|
| 147 |
## Quickstart
|
| 148 |
|
| 149 |
+
End-to-end smoke demo: generate a short video with the diffusers LTX-2.3
|
| 150 |
**distilled** two-stage pipeline, then decode the same latent with the stock
|
| 151 |
LTX-2.3 VAE and with PrunaVAED. Writes two mp4s and prints decode time (ms).
|
| 152 |
Needs a **CUDA GPU**.
|
|
|
|
| 162 |
# 3. Install dependencies
|
| 163 |
pip install -r requirements-test.txt
|
| 164 |
|
| 165 |
+
# 4. Run the demo (~1080p, ~5 s @ 24 fps)
|
| 166 |
python demo/demo_distilled_decode.py
|
| 167 |
```
|
| 168 |
|
| 169 |
+
Outputs land in `outputs/demo_distilled/` (`ltx23.mp4`, `prunavaed.mp4`).
|
| 170 |
+
Edit `PROMPT` / resolution at the top of `demi/demo_distilled_decode.py` if needed.
|
| 171 |
|
| 172 |
|
| 173 |
## Architecture
|