thanks to lambdalabs \\u2764
Browse files- config.yaml +72 -0
- model_index.json +24 -0
- scheduler/scheduler_config.json +20 -0
- text_encoder/config.json +25 -0
- text_encoder/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +33 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +34 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +31 -0
- vae/diffusion_pytorch_model.bin +3 -0
config.yaml
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
pretrained_model_path: /home/ubuntu/models/model_scope_diffusers/
|
2 |
+
output_dir: /home/ubuntu/outputs
|
3 |
+
train_data:
|
4 |
+
width: 1024
|
5 |
+
height: 576
|
6 |
+
use_bucketing: true
|
7 |
+
sample_start_idx: 1
|
8 |
+
fps: 24
|
9 |
+
frame_step: 1
|
10 |
+
n_sample_frames: 24
|
11 |
+
single_video_path: path/to/single/video.mp4
|
12 |
+
single_video_prompt: ''
|
13 |
+
fallback_prompt: ''
|
14 |
+
path: path/to/folder/of/videos/
|
15 |
+
json_path: /home/ubuntu/all.json
|
16 |
+
image_dir: path/to/image/directory
|
17 |
+
single_img_prompt: ''
|
18 |
+
validation_data:
|
19 |
+
prompt: ''
|
20 |
+
sample_preview: false
|
21 |
+
num_frames: 16
|
22 |
+
width: 384
|
23 |
+
height: 384
|
24 |
+
num_inference_steps: 25
|
25 |
+
guidance_scale: 9
|
26 |
+
dataset_types:
|
27 |
+
- json
|
28 |
+
validation_steps: 500
|
29 |
+
extra_unet_params: null
|
30 |
+
extra_text_encoder_params: null
|
31 |
+
train_batch_size: 1
|
32 |
+
max_train_steps: 50000
|
33 |
+
learning_rate: 5.0e-06
|
34 |
+
scale_lr: false
|
35 |
+
lr_scheduler: constant
|
36 |
+
lr_warmup_steps: 0
|
37 |
+
adam_beta1: 0.9
|
38 |
+
adam_beta2: 0.999
|
39 |
+
adam_weight_decay: 0.01
|
40 |
+
adam_epsilon: 1.0e-08
|
41 |
+
max_grad_norm: 1.0
|
42 |
+
gradient_accumulation_steps: 1
|
43 |
+
checkpointing_steps: 5000
|
44 |
+
resume_from_checkpoint: null
|
45 |
+
mixed_precision: fp16
|
46 |
+
use_8bit_adam: false
|
47 |
+
enable_xformers_memory_efficient_attention: false
|
48 |
+
enable_torch_2_attn: true
|
49 |
+
seed: 64
|
50 |
+
extend_dataset: false
|
51 |
+
cached_latent_dir: null
|
52 |
+
use_unet_lora: false
|
53 |
+
unet_lora_modules:
|
54 |
+
- ResnetBlock2D
|
55 |
+
text_encoder_lora_modules:
|
56 |
+
- CLIPEncoderLayer
|
57 |
+
lora_rank: 16
|
58 |
+
lora_path: ''
|
59 |
+
kwargs: {}
|
60 |
+
cache_latents: false
|
61 |
+
gradient_checkpointing: true
|
62 |
+
offset_noise_strength: 0.1
|
63 |
+
text_encoder_gradient_checkpointing: false
|
64 |
+
train_text_encoder: false
|
65 |
+
trainable_modules:
|
66 |
+
- attn1
|
67 |
+
- attn2
|
68 |
+
- temp_conv
|
69 |
+
trainable_text_modules:
|
70 |
+
- all
|
71 |
+
use_offset_noise: false
|
72 |
+
use_text_lora: false
|
model_index.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "TextToVideoSDPipeline",
|
3 |
+
"_diffusers_version": "0.18.0.dev0",
|
4 |
+
"scheduler": [
|
5 |
+
"diffusers",
|
6 |
+
"DDIMScheduler"
|
7 |
+
],
|
8 |
+
"text_encoder": [
|
9 |
+
"transformers",
|
10 |
+
"CLIPTextModel"
|
11 |
+
],
|
12 |
+
"tokenizer": [
|
13 |
+
"transformers",
|
14 |
+
"CLIPTokenizer"
|
15 |
+
],
|
16 |
+
"unet": [
|
17 |
+
"models.unet_3d_condition",
|
18 |
+
"UNet3DConditionModel"
|
19 |
+
],
|
20 |
+
"vae": [
|
21 |
+
"diffusers",
|
22 |
+
"AutoencoderKL"
|
23 |
+
]
|
24 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.18.0.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 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/models/model_scope_diffusers/",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.30.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a06cf32cf585d03b55fef302142a5321b761ec440113925f64f4ceaffc7730
|
3 |
+
size 680904225
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"do_lower_case": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 77,
|
23 |
+
"pad_token": "<|endoftext|>",
|
24 |
+
"tokenizer_class": "CLIPTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet3DConditionModel",
|
3 |
+
"_diffusers_version": "0.18.0.dev0",
|
4 |
+
"_name_or_path": "/home/ubuntu/models/model_scope_diffusers/",
|
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 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da1839762abf114c1785fffe5518c4449d01d277f7ea7521012f38783f1a5937
|
3 |
+
size 2823110385
|
vae/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.18.0.dev0",
|
4 |
+
"_name_or_path": "/home/ubuntu/models/model_scope_diffusers/",
|
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 |
+
"in_channels": 3,
|
19 |
+
"latent_channels": 4,
|
20 |
+
"layers_per_block": 2,
|
21 |
+
"norm_num_groups": 32,
|
22 |
+
"out_channels": 3,
|
23 |
+
"sample_size": 512,
|
24 |
+
"scaling_factor": 0.18215,
|
25 |
+
"up_block_types": [
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D"
|
30 |
+
]
|
31 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b0d11ff25d00ceaa02f602831d9cfe650509fdc850c0a1bcb2acdfa03bd5d56
|
3 |
+
size 167407857
|