Commit
•
93c0855
1
Parent(s):
cc38adf
End of training
Browse files- README.md +46 -0
- feature_extractor/preprocessor_config.json +29 -0
- logs/text2image-fine-tune/1701556246.7813814/events.out.tfevents.1701556246.993071d670e8.18167.1 +3 -0
- logs/text2image-fine-tune/1701556246.7830482/hparams.yml +51 -0
- logs/text2image-fine-tune/events.out.tfevents.1701556246.993071d670e8.18167.0 +3 -0
- model_index.json +38 -0
- scheduler/scheduler_config.json +15 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +30 -0
- tokenizer/tokenizer_config.json +38 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +73 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +32 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
- val_imgs_grid.png +0 -0
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: creativeml-openrail-m
|
4 |
+
base_model: kerianheyi/CS245-fine-tunedSD10600_11000_14122
|
5 |
+
datasets:
|
6 |
+
- jytjyt05/t_to_m7
|
7 |
+
tags:
|
8 |
+
- stable-diffusion
|
9 |
+
- stable-diffusion-diffusers
|
10 |
+
- text-to-image
|
11 |
+
- diffusers
|
12 |
+
inference: true
|
13 |
+
---
|
14 |
+
|
15 |
+
# Text-to-image finetuning - kerianheYi/CS245-fine-tunedSD11000_11400_14122
|
16 |
+
|
17 |
+
This pipeline was finetuned from **kerianheyi/CS245-fine-tunedSD10600_11000_14122** on the **jytjyt05/t_to_m7** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A melSpectrogram for piano solo in Major']:
|
18 |
+
|
19 |
+
![val_imgs_grid](./val_imgs_grid.png)
|
20 |
+
|
21 |
+
|
22 |
+
## Pipeline usage
|
23 |
+
|
24 |
+
You can use the pipeline like so:
|
25 |
+
|
26 |
+
```python
|
27 |
+
from diffusers import DiffusionPipeline
|
28 |
+
import torch
|
29 |
+
|
30 |
+
pipeline = DiffusionPipeline.from_pretrained("kerianheYi/CS245-fine-tunedSD11000_11400_14122", torch_dtype=torch.float16)
|
31 |
+
prompt = "A melSpectrogram for piano solo in Major"
|
32 |
+
image = pipeline(prompt).images[0]
|
33 |
+
image.save("my_image.png")
|
34 |
+
```
|
35 |
+
|
36 |
+
## Training info
|
37 |
+
|
38 |
+
These are the key hyperparameters used during training:
|
39 |
+
|
40 |
+
* Epochs: 1
|
41 |
+
* Learning rate: 1e-05
|
42 |
+
* Batch size: 1
|
43 |
+
* Gradient accumulation steps: 4
|
44 |
+
* Image resolution: 512
|
45 |
+
* Mixed-precision: fp16
|
46 |
+
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
+
"image_mean": [
|
13 |
+
0.48145466,
|
14 |
+
0.4578275,
|
15 |
+
0.40821073
|
16 |
+
],
|
17 |
+
"image_processor_type": "CLIPImageProcessor",
|
18 |
+
"image_std": [
|
19 |
+
0.26862954,
|
20 |
+
0.26130258,
|
21 |
+
0.27577711
|
22 |
+
],
|
23 |
+
"resample": 3,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"shortest_edge": 224
|
27 |
+
},
|
28 |
+
"use_square_size": false
|
29 |
+
}
|
logs/text2image-fine-tune/1701556246.7813814/events.out.tfevents.1701556246.993071d670e8.18167.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3df98114710d3a55a0ba1a4988d6c29fc1cad2371bb22feb4c985395ae7dc159
|
3 |
+
size 2296
|
logs/text2image-fine-tune/1701556246.7830482/hparams.yml
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
cache_dir: null
|
7 |
+
caption_column: caption
|
8 |
+
center_crop: false
|
9 |
+
checkpointing_steps: 100000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: jytjyt05/t_to_m7
|
14 |
+
enable_xformers_memory_efficient_attention: false
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
input_perturbation: 0
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: -1
|
23 |
+
logging_dir: logs
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_samples: null
|
28 |
+
max_train_steps: 400
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
non_ema_revision: null
|
32 |
+
num_train_epochs: 1
|
33 |
+
output_dir: kerianheyi/CS245-fine-tunedSD11000_11400_14122
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: kerianheyi/CS245-fine-tunedSD10600_11000_14122
|
36 |
+
push_to_hub: true
|
37 |
+
random_flip: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: null
|
44 |
+
snr_gamma: null
|
45 |
+
tracker_project_name: text2image-fine-tune
|
46 |
+
train_batch_size: 1
|
47 |
+
train_data_dir: null
|
48 |
+
use_8bit_adam: false
|
49 |
+
use_ema: true
|
50 |
+
validation_epochs: 5
|
51 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1701556246.993071d670e8.18167.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aded19c179dbef9966b4171789914c667a1a8961fa0018e05de3e15ab9e75849
|
3 |
+
size 269417
|
model_index.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.25.0.dev0",
|
4 |
+
"_name_or_path": "kerianheyi/CS245-fine-tunedSD10600_11000_14122",
|
5 |
+
"feature_extractor": [
|
6 |
+
"transformers",
|
7 |
+
"CLIPImageProcessor"
|
8 |
+
],
|
9 |
+
"image_encoder": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"requires_safety_checker": false,
|
14 |
+
"safety_checker": [
|
15 |
+
null,
|
16 |
+
null
|
17 |
+
],
|
18 |
+
"scheduler": [
|
19 |
+
"diffusers",
|
20 |
+
"PNDMScheduler"
|
21 |
+
],
|
22 |
+
"text_encoder": [
|
23 |
+
"transformers",
|
24 |
+
"CLIPTextModel"
|
25 |
+
],
|
26 |
+
"tokenizer": [
|
27 |
+
"transformers",
|
28 |
+
"CLIPTokenizer"
|
29 |
+
],
|
30 |
+
"unet": [
|
31 |
+
"diffusers",
|
32 |
+
"UNet2DConditionModel"
|
33 |
+
],
|
34 |
+
"vae": [
|
35 |
+
"diffusers",
|
36 |
+
"AutoencoderKL"
|
37 |
+
]
|
38 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.25.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"prediction_type": "epsilon",
|
10 |
+
"set_alpha_to_one": false,
|
11 |
+
"skip_prk_steps": true,
|
12 |
+
"steps_offset": 1,
|
13 |
+
"timestep_spacing": "leading",
|
14 |
+
"trained_betas": null
|
15 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kerianheyi/CS245-fine-tunedSD10600_11000_14122",
|
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": "4.35.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
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
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"content": "!",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
31 |
+
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 77,
|
35 |
+
"pad_token": "!",
|
36 |
+
"tokenizer_class": "CLIPTokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.25.0.dev0",
|
4 |
+
"_name_or_path": "kerianheyi/CS245-fine-tunedSD10600_11000_14122",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20,
|
13 |
+
20
|
14 |
+
],
|
15 |
+
"attention_type": "default",
|
16 |
+
"block_out_channels": [
|
17 |
+
320,
|
18 |
+
640,
|
19 |
+
1280,
|
20 |
+
1280
|
21 |
+
],
|
22 |
+
"center_input_sample": false,
|
23 |
+
"class_embed_type": null,
|
24 |
+
"class_embeddings_concat": false,
|
25 |
+
"conv_in_kernel": 3,
|
26 |
+
"conv_out_kernel": 3,
|
27 |
+
"cross_attention_dim": 1024,
|
28 |
+
"cross_attention_norm": null,
|
29 |
+
"down_block_types": [
|
30 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
34 |
+
],
|
35 |
+
"downsample_padding": 1,
|
36 |
+
"dropout": 0.0,
|
37 |
+
"dual_cross_attention": false,
|
38 |
+
"encoder_hid_dim": null,
|
39 |
+
"encoder_hid_dim_type": null,
|
40 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32abbd4876bd3ebff7839d67d23ff9f31e2c9b6eccc1d8dfe12986c24b5f343
|
3 |
+
size 3463726504
|
vae/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.25.0.dev0",
|
4 |
+
"_name_or_path": "kerianheyi/CS245-fine-tunedSD10600_11000_14122",
|
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 |
+
"layers_per_block": 2,
|
22 |
+
"norm_num_groups": 32,
|
23 |
+
"out_channels": 3,
|
24 |
+
"sample_size": 512,
|
25 |
+
"scaling_factor": 0.18215,
|
26 |
+
"up_block_types": [
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D",
|
30 |
+
"UpDecoderBlock2D"
|
31 |
+
]
|
32 |
+
}
|
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
|
val_imgs_grid.png
ADDED
![]() |