Instructions to use TensorStack/AutoEncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TensorStack/AutoEncoder 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/AutoEncoder", 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 2 files
Browse files- LTX23/config.json +93 -93
- LTX23/diffusion_pytorch_model.safetensors +2 -2
LTX23/config.json
CHANGED
|
@@ -1,93 +1,93 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "AutoencoderKLLTX2Video",
|
| 3 |
-
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
-
"block_out_channels": [
|
| 5 |
-
256,
|
| 6 |
-
512,
|
| 7 |
-
1024,
|
| 8 |
-
1024
|
| 9 |
-
],
|
| 10 |
-
"decoder_block_out_channels": [
|
| 11 |
-
256,
|
| 12 |
-
512,
|
| 13 |
-
512,
|
| 14 |
-
1024
|
| 15 |
-
],
|
| 16 |
-
"decoder_causal": false,
|
| 17 |
-
"decoder_inject_noise": [
|
| 18 |
-
false,
|
| 19 |
-
false,
|
| 20 |
-
false,
|
| 21 |
-
false,
|
| 22 |
-
false
|
| 23 |
-
],
|
| 24 |
-
"decoder_layers_per_block": [
|
| 25 |
-
4,
|
| 26 |
-
6,
|
| 27 |
-
4,
|
| 28 |
-
2,
|
| 29 |
-
2
|
| 30 |
-
],
|
| 31 |
-
"decoder_spatial_padding_mode": "
|
| 32 |
-
"decoder_spatio_temporal_scaling": [
|
| 33 |
-
true,
|
| 34 |
-
true,
|
| 35 |
-
true,
|
| 36 |
-
true
|
| 37 |
-
],
|
| 38 |
-
"down_block_types": [
|
| 39 |
-
"LTX2VideoDownBlock3D",
|
| 40 |
-
"LTX2VideoDownBlock3D",
|
| 41 |
-
"LTX2VideoDownBlock3D",
|
| 42 |
-
"LTX2VideoDownBlock3D"
|
| 43 |
-
],
|
| 44 |
-
"downsample_type": [
|
| 45 |
-
"spatial",
|
| 46 |
-
"temporal",
|
| 47 |
-
"spatiotemporal",
|
| 48 |
-
"spatiotemporal"
|
| 49 |
-
],
|
| 50 |
-
"encoder_causal": true,
|
| 51 |
-
"encoder_spatial_padding_mode": "zeros",
|
| 52 |
-
"in_channels": 3,
|
| 53 |
-
"latent_channels": 128,
|
| 54 |
-
"layers_per_block": [
|
| 55 |
-
4,
|
| 56 |
-
6,
|
| 57 |
-
4,
|
| 58 |
-
2,
|
| 59 |
-
2
|
| 60 |
-
],
|
| 61 |
-
"out_channels": 3,
|
| 62 |
-
"patch_size": 4,
|
| 63 |
-
"patch_size_t": 1,
|
| 64 |
-
"resnet_norm_eps": 1e-06,
|
| 65 |
-
"scaling_factor": 1.0,
|
| 66 |
-
"spatial_compression_ratio": 32,
|
| 67 |
-
"spatio_temporal_scaling": [
|
| 68 |
-
true,
|
| 69 |
-
true,
|
| 70 |
-
true,
|
| 71 |
-
true
|
| 72 |
-
],
|
| 73 |
-
"temporal_compression_ratio": 8,
|
| 74 |
-
"timestep_conditioning": false,
|
| 75 |
-
"upsample_factor": [
|
| 76 |
-
2,
|
| 77 |
-
2,
|
| 78 |
-
1,
|
| 79 |
-
2
|
| 80 |
-
],
|
| 81 |
-
"upsample_residual": [
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
],
|
| 87 |
-
"upsample_type": [
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
]
|
| 93 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLLTX2Video",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"block_out_channels": [
|
| 5 |
+
256,
|
| 6 |
+
512,
|
| 7 |
+
1024,
|
| 8 |
+
1024
|
| 9 |
+
],
|
| 10 |
+
"decoder_block_out_channels": [
|
| 11 |
+
256,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
1024
|
| 15 |
+
],
|
| 16 |
+
"decoder_causal": false,
|
| 17 |
+
"decoder_inject_noise": [
|
| 18 |
+
false,
|
| 19 |
+
false,
|
| 20 |
+
false,
|
| 21 |
+
false,
|
| 22 |
+
false
|
| 23 |
+
],
|
| 24 |
+
"decoder_layers_per_block": [
|
| 25 |
+
4,
|
| 26 |
+
6,
|
| 27 |
+
4,
|
| 28 |
+
2,
|
| 29 |
+
2
|
| 30 |
+
],
|
| 31 |
+
"decoder_spatial_padding_mode": "zeros",
|
| 32 |
+
"decoder_spatio_temporal_scaling": [
|
| 33 |
+
true,
|
| 34 |
+
true,
|
| 35 |
+
true,
|
| 36 |
+
true
|
| 37 |
+
],
|
| 38 |
+
"down_block_types": [
|
| 39 |
+
"LTX2VideoDownBlock3D",
|
| 40 |
+
"LTX2VideoDownBlock3D",
|
| 41 |
+
"LTX2VideoDownBlock3D",
|
| 42 |
+
"LTX2VideoDownBlock3D"
|
| 43 |
+
],
|
| 44 |
+
"downsample_type": [
|
| 45 |
+
"spatial",
|
| 46 |
+
"temporal",
|
| 47 |
+
"spatiotemporal",
|
| 48 |
+
"spatiotemporal"
|
| 49 |
+
],
|
| 50 |
+
"encoder_causal": true,
|
| 51 |
+
"encoder_spatial_padding_mode": "zeros",
|
| 52 |
+
"in_channels": 3,
|
| 53 |
+
"latent_channels": 128,
|
| 54 |
+
"layers_per_block": [
|
| 55 |
+
4,
|
| 56 |
+
6,
|
| 57 |
+
4,
|
| 58 |
+
2,
|
| 59 |
+
2
|
| 60 |
+
],
|
| 61 |
+
"out_channels": 3,
|
| 62 |
+
"patch_size": 4,
|
| 63 |
+
"patch_size_t": 1,
|
| 64 |
+
"resnet_norm_eps": 1e-06,
|
| 65 |
+
"scaling_factor": 1.0,
|
| 66 |
+
"spatial_compression_ratio": 32,
|
| 67 |
+
"spatio_temporal_scaling": [
|
| 68 |
+
true,
|
| 69 |
+
true,
|
| 70 |
+
true,
|
| 71 |
+
true
|
| 72 |
+
],
|
| 73 |
+
"temporal_compression_ratio": 8,
|
| 74 |
+
"timestep_conditioning": false,
|
| 75 |
+
"upsample_factor": [
|
| 76 |
+
2,
|
| 77 |
+
2,
|
| 78 |
+
1,
|
| 79 |
+
2
|
| 80 |
+
],
|
| 81 |
+
"upsample_residual": [
|
| 82 |
+
false,
|
| 83 |
+
false,
|
| 84 |
+
false,
|
| 85 |
+
false
|
| 86 |
+
],
|
| 87 |
+
"upsample_type": [
|
| 88 |
+
"spatiotemporal",
|
| 89 |
+
"spatiotemporal",
|
| 90 |
+
"temporal",
|
| 91 |
+
"spatial"
|
| 92 |
+
]
|
| 93 |
+
}
|
LTX23/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:425f0dfa227dee5d0ff3d9720563370810409a439c302ca74f0f944057ce55c5
|
| 3 |
+
size 1452233194
|