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 tests/test_distilled_decode.py
Browse files
tests/test_distilled_decode.py
CHANGED
|
@@ -46,16 +46,12 @@ LTX23_VAE = "diffusers/LTX-2.3-Diffusers" # stock decoder (baseline)
|
|
| 46 |
PRUNED_VAE = REPO_ROOT # this repo's vae/ folder
|
| 47 |
|
| 48 |
# ~720p for 5 s @ 24 fps. Height/width must be multiples of 64 (2-stage).
|
| 49 |
-
HEIGHT, WIDTH, NUM_FRAMES, FPS =
|
| 50 |
SEED = 42
|
| 51 |
DECODE_WARMUP, DECODE_RUNS = 1, 3 # timing: 1 warm-up + median of 3 runs
|
| 52 |
|
| 53 |
PROMPT = (
|
| 54 |
-
|
| 55 |
-
"He is wearing a black cap, a grey t-shirt, and black pants. The skate park "
|
| 56 |
-
"has a wooden floor and a ramp. The man performs a trick by jumping and "
|
| 57 |
-
"flipping the skateboard under his feet while in the air. He lands on the "
|
| 58 |
-
"skateboard and continues to ride it."
|
| 59 |
)
|
| 60 |
|
| 61 |
DEVICE = "cuda"
|
|
|
|
| 46 |
PRUNED_VAE = REPO_ROOT # this repo's vae/ folder
|
| 47 |
|
| 48 |
# ~720p for 5 s @ 24 fps. Height/width must be multiples of 64 (2-stage).
|
| 49 |
+
HEIGHT, WIDTH, NUM_FRAMES, FPS = 1088, 1920, 121, 24.0
|
| 50 |
SEED = 42
|
| 51 |
DECODE_WARMUP, DECODE_RUNS = 1, 3 # timing: 1 warm-up + median of 3 runs
|
| 52 |
|
| 53 |
PROMPT = (
|
| 54 |
+
"The video shows a hockey player in a green jersey and blue helmet skating on the ice with a hockey stick. The player is seen moving around the ice, passing the puck to another player who is also wearing a green jersey and blue helmet. The player in the green jersey is seen skating away from the camera, and then turning around to face the camera. The ice rink is surrounded by boards with advertisements, and there are other players in the background. The player in the green jersey is wearing black gloves and black skates. The player in the green jersey is also seen skating towards the camera and then away from the camera again."
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
)
|
| 56 |
|
| 57 |
DEVICE = "cuda"
|