Instructions to use fal/LTX-2.3-FlashPack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/LTX-2.3-FlashPack with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fal/LTX-2.3-FlashPack", 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
| { | |
| "_class_name": "LTX2EmbeddingsProcessorModel", | |
| "_diffusers_version": "0.37.0", | |
| "audio_apply_gated_attention": true, | |
| "audio_attention_head_dim": 64, | |
| "audio_double_precision_rope": true, | |
| "audio_num_attention_heads": 32, | |
| "audio_num_layers": 8, | |
| "audio_positional_embedding_max_pos": [ | |
| 4096 | |
| ], | |
| "audio_rope_type": "split", | |
| "feature_extractor_audio_dim": 2048, | |
| "feature_extractor_embedding_dim": 3840, | |
| "feature_extractor_flat_dim": 188160, | |
| "feature_extractor_video_dim": 4096, | |
| "video_apply_gated_attention": true, | |
| "video_attention_head_dim": 128, | |
| "video_double_precision_rope": true, | |
| "video_num_attention_heads": 32, | |
| "video_num_layers": 8, | |
| "video_positional_embedding_max_pos": [ | |
| 4096 | |
| ], | |
| "video_rope_type": "split" | |
| } | |