Instructions to use TensorStack/Components with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TensorStack/Components with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TensorStack/Components", 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 8 files
Browse files- LTX20_AudioVae/config.json +25 -0
- LTX20_AudioVae/diffusion_pytorch_model.safetensors +3 -0
- LTX20_Connectors/config.json +19 -0
- LTX20_Connectors/diffusion_pytorch_model.safetensors +3 -0
- LTX20_Upsampler/config.json +11 -0
- LTX20_Upsampler/diffusion_pytorch_model.safetensors +3 -0
- LTX20_Vocoder/config.json +45 -0
- LTX20_Vocoder/diffusion_pytorch_model.safetensors +3 -0
LTX20_AudioVae/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLLTX2Audio",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"attn_resolutions": null,
|
| 5 |
+
"base_channels": 128,
|
| 6 |
+
"causality_axis": "height",
|
| 7 |
+
"ch_mult": [
|
| 8 |
+
1,
|
| 9 |
+
2,
|
| 10 |
+
4
|
| 11 |
+
],
|
| 12 |
+
"double_z": true,
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"in_channels": 2,
|
| 15 |
+
"is_causal": true,
|
| 16 |
+
"latent_channels": 8,
|
| 17 |
+
"mel_bins": 64,
|
| 18 |
+
"mel_hop_length": 160,
|
| 19 |
+
"mid_block_add_attention": false,
|
| 20 |
+
"norm_type": "pixel",
|
| 21 |
+
"num_res_blocks": 2,
|
| 22 |
+
"output_channels": 2,
|
| 23 |
+
"resolution": 256,
|
| 24 |
+
"sample_rate": 16000
|
| 25 |
+
}
|
LTX20_AudioVae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b36ce4066065ce0aa5ff4d7cf96a3e3bc0859c6fefcf864663e3fe686c5c181c
|
| 3 |
+
size 106507972
|
LTX20_Connectors/config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "LTX2TextConnectors",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"audio_connector_attention_head_dim": 128,
|
| 5 |
+
"audio_connector_num_attention_heads": 30,
|
| 6 |
+
"audio_connector_num_layers": 2,
|
| 7 |
+
"audio_connector_num_learnable_registers": 128,
|
| 8 |
+
"caption_channels": 3840,
|
| 9 |
+
"causal_temporal_positioning": false,
|
| 10 |
+
"connector_rope_base_seq_len": 4096,
|
| 11 |
+
"rope_double_precision": true,
|
| 12 |
+
"rope_theta": 10000.0,
|
| 13 |
+
"rope_type": "split",
|
| 14 |
+
"text_proj_in_factor": 49,
|
| 15 |
+
"video_connector_attention_head_dim": 128,
|
| 16 |
+
"video_connector_num_attention_heads": 30,
|
| 17 |
+
"video_connector_num_layers": 2,
|
| 18 |
+
"video_connector_num_learnable_registers": 128
|
| 19 |
+
}
|
LTX20_Connectors/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c0ad36c2d0706fb229193d5c698f0ef50c9b33678140b4ee84723a047b4032
|
| 3 |
+
size 2862957976
|
LTX20_Upsampler/config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "LTX2LatentUpsamplerModel",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"dims": 3,
|
| 5 |
+
"in_channels": 128,
|
| 6 |
+
"mid_channels": 1024,
|
| 7 |
+
"num_blocks_per_stage": 4,
|
| 8 |
+
"rational_spatial_scale": 2.0,
|
| 9 |
+
"spatial_upsample": true,
|
| 10 |
+
"temporal_upsample": false
|
| 11 |
+
}
|
LTX20_Upsampler/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c07f97ea335a2cd28402e85194227716eca760e99331d6529d160c3199a425f0
|
| 3 |
+
size 995743288
|
LTX20_Vocoder/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "LTX2Vocoder",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"hidden_channels": 1024,
|
| 5 |
+
"in_channels": 128,
|
| 6 |
+
"leaky_relu_negative_slope": 0.1,
|
| 7 |
+
"out_channels": 2,
|
| 8 |
+
"output_sampling_rate": 24000,
|
| 9 |
+
"resnet_dilations": [
|
| 10 |
+
[
|
| 11 |
+
1,
|
| 12 |
+
3,
|
| 13 |
+
5
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
1,
|
| 17 |
+
3,
|
| 18 |
+
5
|
| 19 |
+
],
|
| 20 |
+
[
|
| 21 |
+
1,
|
| 22 |
+
3,
|
| 23 |
+
5
|
| 24 |
+
]
|
| 25 |
+
],
|
| 26 |
+
"resnet_kernel_sizes": [
|
| 27 |
+
3,
|
| 28 |
+
7,
|
| 29 |
+
11
|
| 30 |
+
],
|
| 31 |
+
"upsample_factors": [
|
| 32 |
+
6,
|
| 33 |
+
5,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2
|
| 37 |
+
],
|
| 38 |
+
"upsample_kernel_sizes": [
|
| 39 |
+
16,
|
| 40 |
+
15,
|
| 41 |
+
8,
|
| 42 |
+
4,
|
| 43 |
+
4
|
| 44 |
+
]
|
| 45 |
+
}
|
LTX20_Vocoder/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15855fc59233b9cac50bdd1f0d2ccea4a5eaedbd7fd7549b16d5ebd6cc47d92a
|
| 3 |
+
size 111204124
|