Instructions to use Lightricks/LTX-Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-Video with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-Video", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Create transformer_config.json
Browse files
transformer/transformer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Transformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.25.1",
|
| 4 |
+
"_name_or_path": "PixArt-alpha/PixArt-XL-2-256x256",
|
| 5 |
+
"activation_fn": "gelu-approximate",
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_head_dim": 64,
|
| 8 |
+
"attention_type": "default",
|
| 9 |
+
"caption_channels": 4096,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"double_self_attention": false,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"in_channels": 128,
|
| 14 |
+
"norm_elementwise_affine": false,
|
| 15 |
+
"norm_eps": 1e-06,
|
| 16 |
+
"norm_num_groups": 32,
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_embeds_ada_norm": 1000,
|
| 19 |
+
"num_layers": 28,
|
| 20 |
+
"num_vector_embeds": null,
|
| 21 |
+
"only_cross_attention": false,
|
| 22 |
+
"out_channels": 128,
|
| 23 |
+
"project_to_2d_pos": true,
|
| 24 |
+
"upcast_attention": false,
|
| 25 |
+
"use_linear_projection": false,
|
| 26 |
+
"qk_norm": "rms_norm",
|
| 27 |
+
"standardization_norm": "rms_norm",
|
| 28 |
+
"positional_embedding_type": "rope",
|
| 29 |
+
"positional_embedding_theta": 10000.0,
|
| 30 |
+
"positional_embedding_max_pos": [20, 2048, 2048],
|
| 31 |
+
"timestep_scale_multiplier": 1000
|
| 32 |
+
}
|