Commit
•
4f20fcf
1
Parent(s):
756b660
End of training
Browse files- README.md +68 -0
- feature_extractor/preprocessor_config.json +44 -0
- model_index.json +38 -0
- safety_checker/config.json +28 -0
- safety_checker/model.safetensors +3 -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 +24 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +68 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +34 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
- val_imgs_grid.png +0 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
library_name: diffusers
|
4 |
+
tags:
|
5 |
+
- stable-diffusion
|
6 |
+
- stable-diffusion-diffusers
|
7 |
+
- text-to-image
|
8 |
+
- diffusers
|
9 |
+
- diffusers-training
|
10 |
+
base_model: CompVis/stable-diffusion-v1-4
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
|
18 |
+
# Text-to-image finetuning - MohamedAcadys/PointConImageModelV1-4-V2
|
19 |
+
|
20 |
+
This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **Acadys/PointConImagesV2** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Un patron en costume donne un dossier à un employé']:
|
21 |
+
|
22 |
+
![val_imgs_grid](./val_imgs_grid.png)
|
23 |
+
|
24 |
+
|
25 |
+
## Pipeline usage
|
26 |
+
|
27 |
+
You can use the pipeline like so:
|
28 |
+
|
29 |
+
```python
|
30 |
+
from diffusers import DiffusionPipeline
|
31 |
+
import torch
|
32 |
+
|
33 |
+
pipeline = DiffusionPipeline.from_pretrained("MohamedAcadys/PointConImageModelV1-4-V2", torch_dtype=torch.float16)
|
34 |
+
prompt = "Un patron en costume donne un dossier à un employé"
|
35 |
+
image = pipeline(prompt).images[0]
|
36 |
+
image.save("my_image.png")
|
37 |
+
```
|
38 |
+
|
39 |
+
## Training info
|
40 |
+
|
41 |
+
These are the key hyperparameters used during training:
|
42 |
+
|
43 |
+
* Epochs: 45
|
44 |
+
* Learning rate: 0.0001
|
45 |
+
* Batch size: 4
|
46 |
+
* Gradient accumulation steps: 8
|
47 |
+
* Image resolution: 512
|
48 |
+
* Mixed-precision: fp16
|
49 |
+
|
50 |
+
|
51 |
+
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/acadys-sadadou/text2image-fine-tune/runs/75ycsmt7).
|
52 |
+
|
53 |
+
|
54 |
+
## Intended uses & limitations
|
55 |
+
|
56 |
+
#### How to use
|
57 |
+
|
58 |
+
```python
|
59 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
60 |
+
```
|
61 |
+
|
62 |
+
#### Limitations and bias
|
63 |
+
|
64 |
+
[TODO: provide examples of latent issues and potential remediations]
|
65 |
+
|
66 |
+
## Training details
|
67 |
+
|
68 |
+
[TODO: describe the data used to train the model]
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"crop_size": {
|
20 |
+
"height": 224,
|
21 |
+
"width": 224
|
22 |
+
},
|
23 |
+
"do_center_crop": true,
|
24 |
+
"do_convert_rgb": true,
|
25 |
+
"do_normalize": true,
|
26 |
+
"do_rescale": true,
|
27 |
+
"do_resize": true,
|
28 |
+
"image_mean": [
|
29 |
+
0.48145466,
|
30 |
+
0.4578275,
|
31 |
+
0.40821073
|
32 |
+
],
|
33 |
+
"image_processor_type": "CLIPImageProcessor",
|
34 |
+
"image_std": [
|
35 |
+
0.26862954,
|
36 |
+
0.26130258,
|
37 |
+
0.27577711
|
38 |
+
],
|
39 |
+
"resample": 3,
|
40 |
+
"rescale_factor": 0.00392156862745098,
|
41 |
+
"size": {
|
42 |
+
"shortest_edge": 224
|
43 |
+
}
|
44 |
+
}
|
model_index.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
5 |
+
"feature_extractor": [
|
6 |
+
"transformers",
|
7 |
+
"CLIPImageProcessor"
|
8 |
+
],
|
9 |
+
"image_encoder": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"requires_safety_checker": true,
|
14 |
+
"safety_checker": [
|
15 |
+
"stable_diffusion",
|
16 |
+
"StableDiffusionSafetyChecker"
|
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 |
+
}
|
safety_checker/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
|
3 |
+
"architectures": [
|
4 |
+
"StableDiffusionSafetyChecker"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"logit_scale_init_value": 2.6592,
|
8 |
+
"model_type": "clip",
|
9 |
+
"projection_dim": 768,
|
10 |
+
"text_config": {
|
11 |
+
"dropout": 0.0,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"model_type": "clip_text_model",
|
15 |
+
"num_attention_heads": 12
|
16 |
+
},
|
17 |
+
"torch_dtype": "float32",
|
18 |
+
"transformers_version": "4.40.2",
|
19 |
+
"vision_config": {
|
20 |
+
"dropout": 0.0,
|
21 |
+
"hidden_size": 1024,
|
22 |
+
"intermediate_size": 4096,
|
23 |
+
"model_type": "clip_vision_model",
|
24 |
+
"num_attention_heads": 16,
|
25 |
+
"num_hidden_layers": 24,
|
26 |
+
"patch_size": 14
|
27 |
+
}
|
28 |
+
}
|
safety_checker/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
3 |
+
size 1215979664
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.28.0.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": "CompVis/stable-diffusion-v1-4",
|
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": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.40.2",
|
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 sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
|
3 |
+
size 246144152
|
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": "<|endoftext|>",
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_lower_case": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 77,
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"tokenizer_class": "CLIPTokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66453efe292e7e03b3a9abb5f64dc670917b8114a59c7e975df42dadf66d74c0
|
3 |
+
size 3438167536
|
vae/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"norm_num_groups": 32,
|
25 |
+
"out_channels": 3,
|
26 |
+
"sample_size": 512,
|
27 |
+
"scaling_factor": 0.18215,
|
28 |
+
"up_block_types": [
|
29 |
+
"UpDecoderBlock2D",
|
30 |
+
"UpDecoderBlock2D",
|
31 |
+
"UpDecoderBlock2D",
|
32 |
+
"UpDecoderBlock2D"
|
33 |
+
]
|
34 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
|
3 |
+
size 167335342
|
val_imgs_grid.png
ADDED
![]() |