Hugging Face's logo

TensorStack
/
Components

Diffusers
Safetensors
Model card Files
xet
 Community
saddam213 commited on
Commit
82709cf
·
verified ·
1 Parent(s): dbd47e3

Upload 8 files

Browse files
Files changed (8) hide show
  1. LTX23_AudioVae/config.json +25 -0
  2. LTX23_AudioVae/diffusion_pytorch_model.safetensors +3 -0
  3. LTX23_Connectors/config.json +20 -0
  4. LTX23_Connectors/diffusion_pytorch_model.safetensors +3 -0
  5. LTX23_Upsampler/config.json +11 -0
  6. LTX23_Upsampler/diffusion_pytorch_model.safetensors +3 -0
  7. LTX23_Vocoder/config.json +6 -0
  8. LTX23_Vocoder/diffusion_pytorch_model.safetensors +3 -0
LTX23_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
+ }
LTX23_AudioVae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0efa51a43fe510df0f3108d951a2bc31645b5936dbb6123742184cf451f992
3
+ size 106507940
LTX23_Connectors/config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2TextConnectors",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "audio_connector_attention_head_dim": 64,
5
+ "audio_connector_num_attention_heads": 32,
6
+ "audio_connector_num_layers": 8,
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": "interleaved",
14
+ "text_proj_in_factor": 49,
15
+ "video_connector_attention_head_dim": 128,
16
+ "video_connector_num_attention_heads": 32,
17
+ "video_connector_num_layers": 8,
18
+ "video_connector_num_learnable_registers": 128,
19
+ "apply_gated_attention": true
20
+ }
LTX23_Connectors/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c455a1b365b3ba2d15a9c6e068c1e209eebc3bfef87e1fe0a5a9c65d98833fc0
3
+ size 6344489088
LTX23_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
+ }
LTX23_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
LTX23_Vocoder/config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2Vocoder",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "hop_length": 512,
5
+ "sample_rate": 44100
6
+ }
LTX23_Vocoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64c7e94f0744ec68d04df6616bf5a8369bc20c41addb82f8ad5086fea2386f2
3
+ size 258308856