jbilcke-hf HF staff commited on
Commit
5a016e3
1 Parent(s): 7af6371

Upload 6 files

Browse files
cogvideox-5b-tora/fuser/fuser.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68005dfecd4db6fdb96cce364d094f1c59a36772fd8ded980519ed13a9e176ad
3
+ size 1338924336
cogvideox-5b-tora/model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "CogVideoXPipeline",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "CogVideoXDDIMScheduler"
7
+ ],
8
+ "text_encoder": [
9
+ "transformers",
10
+ "T5EncoderModel"
11
+ ],
12
+ "tokenizer": [
13
+ "transformers",
14
+ "T5Tokenizer"
15
+ ],
16
+ "transformer": [
17
+ "diffusers",
18
+ "CogVideoXTransformer3DModel"
19
+ ],
20
+ "vae": [
21
+ "diffusers",
22
+ "AutoencoderKLCogVideoX"
23
+ ]
24
+ }
cogvideox-5b-tora/scheduler/scheduler_scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "CogVideoXDDIMScheduler",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "v_prediction",
11
+ "rescale_betas_zero_snr": true,
12
+ "sample_max_value": 1.0,
13
+ "set_alpha_to_one": true,
14
+ "snr_shift_scale": 1.0,
15
+ "steps_offset": 0,
16
+ "timestep_spacing": "trailing",
17
+ "trained_betas": null
18
+ }
cogvideox-5b-tora/traj_extractor/traj_extractor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689f6748b865c2ee401c297fe31c2fdf4c5deefae54b4eb6646111bcc5ee7d86
3
+ size 50015368
cogvideox-5b-tora/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd47d57ad948ff80da0af0cb2e4dcdef65073aba59bccfd383ada9a7d1c02024
3
+ size 431221142
cogvideox-5b-tora/vae/vae_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLCogVideoX",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 256,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "CogVideoXDownBlock3D",
13
+ "CogVideoXDownBlock3D",
14
+ "CogVideoXDownBlock3D",
15
+ "CogVideoXDownBlock3D"
16
+ ],
17
+ "force_upcast": true,
18
+ "in_channels": 3,
19
+ "latent_channels": 16,
20
+ "latents_mean": null,
21
+ "latents_std": null,
22
+ "layers_per_block": 3,
23
+ "norm_eps": 1e-06,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_height": 480,
27
+ "sample_width": 720,
28
+ "scaling_factor": 0.7,
29
+ "shift_factor": null,
30
+ "temporal_compression_ratio": 4,
31
+ "up_block_types": [
32
+ "CogVideoXUpBlock3D",
33
+ "CogVideoXUpBlock3D",
34
+ "CogVideoXUpBlock3D",
35
+ "CogVideoXUpBlock3D"
36
+ ],
37
+ "use_post_quant_conv": false,
38
+ "use_quant_conv": false
39
+ }