Hugging Face's logo

heboya8
/
text2video-test-f

Diffusers
Safetensors
TextToVideoSDPipeline
Model card Files
xet
Community
heboya8 commited on
Commit
a9428dd
·
verified ·
1 Parent(s): 77e549d

Add files using upload-large-folder tool

Browse files
Files changed (17) hide show
  1. checkpoint-20000/unet/diffusion_pytorch_model.safetensors +1 -1
  2. checkpoint-40000/unet/diffusion_pytorch_model.safetensors +1 -1
  3. checkpoint-60000/lora/full_weights/60000_lora_text_to_video_unet.safetensors +3 -0
  4. checkpoint-60000/model_index.json +25 -0
  5. checkpoint-60000/scheduler/scheduler_config.json +20 -0
  6. checkpoint-60000/text_encoder/config.json +24 -0
  7. checkpoint-60000/text_encoder/model.safetensors +3 -0
  8. checkpoint-60000/tokenizer/merges.txt +0 -0
  9. checkpoint-60000/tokenizer/special_tokens_map.json +24 -0
  10. checkpoint-60000/tokenizer/tokenizer_config.json +39 -0
  11. checkpoint-60000/tokenizer/vocab.json +0 -0
  12. checkpoint-60000/unet/config.json +34 -0
  13. checkpoint-60000/unet/diffusion_pytorch_model.safetensors +3 -0
  14. checkpoint-60000/vae/config.json +38 -0
  15. checkpoint-60000/vae/diffusion_pytorch_model.safetensors +3 -0
  16. config.yaml +1 -1
  17. lora/full_weights/61005_lora_text_to_video_unet.safetensors +3 -0
checkpoint-20000/unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f4accb534fad07264e9d155b39be1aa2a83dc86b7b3aa00ebd3ba6290c0dd86
3
  size 5645118400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9ee6bf9033eeb5af7c85aa758911d0509870076e70d2b032183452dc47fdba
3
  size 5645118400
checkpoint-40000/unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59e6e14fb444d63d55730c2c56451de3e4f16cf6c2116ed3a201b81aee35b5dd
3
  size 5645118400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc321e7cc69b51dd15d85075b2fbd2d60151370af953c037c7ef63829c73b85
3
  size 5645118400
checkpoint-60000/lora/full_weights/60000_lora_text_to_video_unet.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbcbf73561f6bc5d0a17ea6a2081feed2d1304e87602d8c502d9a5c4bd85576
3
+ size 16
checkpoint-60000/model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "TextToVideoSDPipeline",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "/kaggle/input/my-text2video-1-7b",
5
+ "scheduler": [
6
+ "diffusers",
7
+ "DDIMScheduler"
8
+ ],
9
+ "text_encoder": [
10
+ "transformers",
11
+ "CLIPTextModel"
12
+ ],
13
+ "tokenizer": [
14
+ "transformers",
15
+ "CLIPTokenizer"
16
+ ],
17
+ "unet": [
18
+ "models.unet_3d_condition",
19
+ "UNet3DConditionModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKL"
24
+ ]
25
+ }
checkpoint-60000/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.34.0.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
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
+ "trained_betas": null
20
+ }
checkpoint-60000/text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 1024,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 23,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 512,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.51.3",
23
+ "vocab_size": 49408
24
+ }
checkpoint-60000/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
3
+ size 680820392
checkpoint-60000/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-60000/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-60000/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|startoftext|>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "extra_special_tokens": {},
35
+ "model_max_length": 77,
36
+ "pad_token": "!",
37
+ "tokenizer_class": "CLIPTokenizer",
38
+ "unk_token": "<|endoftext|>"
39
+ }
checkpoint-60000/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-60000/unet/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet3DConditionModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "/kaggle/input/my-text2video-1-7b",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 64,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "cross_attention_dim": 1024,
14
+ "down_block_types": [
15
+ "CrossAttnDownBlock3D",
16
+ "CrossAttnDownBlock3D",
17
+ "CrossAttnDownBlock3D",
18
+ "DownBlock3D"
19
+ ],
20
+ "downsample_padding": 1,
21
+ "in_channels": 4,
22
+ "layers_per_block": 2,
23
+ "mid_block_scale_factor": 1,
24
+ "norm_eps": 1e-05,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 4,
27
+ "sample_size": 32,
28
+ "up_block_types": [
29
+ "UpBlock3D",
30
+ "CrossAttnUpBlock3D",
31
+ "CrossAttnUpBlock3D",
32
+ "CrossAttnUpBlock3D"
33
+ ]
34
+ }
checkpoint-60000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a980ee498fc3161c454615aaef2f9e0d7f1eba4b184835d3b1517d446b9c5db5
3
+ size 5645118400
checkpoint-60000/vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "/kaggle/input/my-text2video-1-7b",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 3,
27
+ "sample_size": 512,
28
+ "scaling_factor": 0.18215,
29
+ "shift_factor": null,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": true,
37
+ "use_quant_conv": true
38
+ }
checkpoint-60000/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342
config.yaml CHANGED
@@ -32,7 +32,7 @@ trainable_text_modules: null
32
  extra_unet_params: null
33
  extra_text_encoder_params: null
34
  train_batch_size: 1
35
- max_train_steps: 60000
36
  learning_rate: 1.0e-05
37
  scale_lr: false
38
  lr_scheduler: constant
 
32
  extra_unet_params: null
33
  extra_text_encoder_params: null
34
  train_batch_size: 1
35
+ max_train_steps: 64000
36
  learning_rate: 1.0e-05
37
  scale_lr: false
38
  lr_scheduler: constant
lora/full_weights/61005_lora_text_to_video_unet.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbcbf73561f6bc5d0a17ea6a2081feed2d1304e87602d8c502d9a5c4bd85576
3
+ size 16