End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +4 -0
- README.md +45 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/unet/config.json +73 -0
- checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- checkpoint-200/optimizer.bin +3 -0
- checkpoint-200/random_states_0.pkl +3 -0
- checkpoint-200/scaler.pt +3 -0
- checkpoint-200/scheduler.bin +3 -0
- checkpoint-200/unet/config.json +73 -0
- checkpoint-200/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-200/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-200/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- checkpoint-400/optimizer.bin +3 -0
- checkpoint-400/random_states_0.pkl +3 -0
- checkpoint-400/scaler.pt +3 -0
- checkpoint-400/scheduler.bin +3 -0
- checkpoint-400/unet/config.json +73 -0
- checkpoint-400/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-400/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-400/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- checkpoint-600/optimizer.bin +3 -0
- checkpoint-600/random_states_0.pkl +3 -0
- checkpoint-600/scaler.pt +3 -0
- checkpoint-600/scheduler.bin +3 -0
- checkpoint-600/unet/config.json +73 -0
- checkpoint-600/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-600/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-600/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- checkpoint-800/optimizer.bin +3 -0
- checkpoint-800/random_states_0.pkl +3 -0
- checkpoint-800/scaler.pt +3 -0
- checkpoint-800/scheduler.bin +3 -0
- checkpoint-800/unet/config.json +73 -0
- checkpoint-800/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-800/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-800/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- image_0.png +3 -0
- image_1.png +3 -0
- image_2.png +3 -0
- image_3.png +3 -0
- model_index.json +42 -0
- scheduler/scheduler_config.json +25 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
image_0.png filter=lfs diff=lfs merge=lfs -text
|
37 |
+
image_1.png filter=lfs diff=lfs merge=lfs -text
|
38 |
+
image_2.png filter=lfs diff=lfs merge=lfs -text
|
39 |
+
image_3.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
3 |
+
library_name: diffusers
|
4 |
+
license: creativeml-openrail-m
|
5 |
+
inference: true
|
6 |
+
tags:
|
7 |
+
- stable-diffusion-xl
|
8 |
+
- stable-diffusion-xl-diffusers
|
9 |
+
- text-to-image
|
10 |
+
- diffusers-training
|
11 |
+
- diffusers
|
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 - seungminh/ndxl_test
|
19 |
+
|
20 |
+
This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **seungminh/ndot_subset_random** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: beautiful scenery nature glass bottle landscape, purple galaxy bottle:
|
21 |
+
|
22 |
+
![img_0](./image_0.png)
|
23 |
+
![img_1](./image_1.png)
|
24 |
+
![img_2](./image_2.png)
|
25 |
+
![img_3](./image_3.png)
|
26 |
+
|
27 |
+
|
28 |
+
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
29 |
+
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
#### How to use
|
34 |
+
|
35 |
+
```python
|
36 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
37 |
+
```
|
38 |
+
|
39 |
+
#### Limitations and bias
|
40 |
+
|
41 |
+
[TODO: provide examples of latent issues and potential remediations]
|
42 |
+
|
43 |
+
## Training details
|
44 |
+
|
45 |
+
[TODO: describe the data used to train the model]
|
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53c6648300b0fa6f801cee6107be7206b91d9729c8d918df66f61ff2b6bc5378
|
3 |
+
size 5222141436
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8461a10663cb6115bec0f1f492be911c6f9e1f2a87c961d652e55f0a43b76bf
|
3 |
+
size 14344
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
|
3 |
+
size 988
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cc9d529863b9458dbb9b91d10c2e89741ffa38f99dbc44be25770289ed29416
|
3 |
+
size 1000
|
checkpoint-1000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16dbb74d4784f9f5d02d5aa0a4cc04e465ce2b5b4a27b826a40d6f9432fe3e92
|
3 |
+
size 9988139160
|
checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:790769feb0ed7a2390e42f9c9144d99f66d9692115b4e733ebb8c12c679c5f75
|
3 |
+
size 281938304
|
checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ad858636bd1aa18013890dc66ac3b5d896b4ee43aad823939b60cf0d2bc097c
|
3 |
+
size 5222139772
|
checkpoint-200/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee4a573f258ada84fffa109e355567f0d4a18e65acd560544f6a7cbfdab0591d
|
3 |
+
size 14344
|
checkpoint-200/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd55b3848d82967a207e0805911c79200c6adce71e3b37fd24549a718f75738
|
3 |
+
size 988
|
checkpoint-200/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa41152562e90f820cd8d847d8cfef38acaada6709d627eb4cde10531d6a002
|
3 |
+
size 1000
|
checkpoint-200/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-200/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:705a63bd3f256ab413b5bddb488afc2b52fc5cdc4f59a45203efc950e054cd6f
|
3 |
+
size 9988139160
|
checkpoint-200/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c18a2085455704ac7535fb509f9055c87c9d327e041825e0127ab334e747948c
|
3 |
+
size 281938304
|
checkpoint-200/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-400/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ee22d461e2655ee2bb63b81351962396996bf78250209885d460e161fd3b651
|
3 |
+
size 5222141436
|
checkpoint-400/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a81a13831461bbf5bc7d975ed7b07a87bf93bbf51819e62831524dd106f574
|
3 |
+
size 14344
|
checkpoint-400/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c801982aae9be06d302403c1fff693e53dedf89c1d3b689ee29fedad84a96d23
|
3 |
+
size 988
|
checkpoint-400/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85ff3810d83f0315479bff9e354b8a08aed7471bec6e14d46e165fadeadba340
|
3 |
+
size 1000
|
checkpoint-400/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-400/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fcb9ac64bc099e13a69bbcdc27aef08a73695b2276550330814c70d9726b231
|
3 |
+
size 9988139160
|
checkpoint-400/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0434dcc461b1f9b1fd06c7dc65dc5ebec4ea86759325947335d402d6cf9ed136
|
3 |
+
size 281938304
|
checkpoint-400/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-600/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42cbb8bb6c4950413d7df30df43d39797588b2055b780ce7cd8d975f96ffd13e
|
3 |
+
size 5222141436
|
checkpoint-600/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:693324ecadf803a487022df78facab0a7e1cfb4b4a3db569e6fb5a25032148bf
|
3 |
+
size 14408
|
checkpoint-600/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e32b8db4f4cba2b7b0157ab60a064591c3802a9067529d5fddbb1c6c1e99660b
|
3 |
+
size 988
|
checkpoint-600/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05610676ed149d854d87e17503a2b6cd63be5d35325fd82390094dcc3fb21f57
|
3 |
+
size 1000
|
checkpoint-600/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-600/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1631f9f75879d8a8c99d36d1a7616d9394a87bb557c948230bae3697a7f1e542
|
3 |
+
size 9988139160
|
checkpoint-600/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45029bb7229609ba0469047634d854680c6c5bdcb2784bc40ba5057e26db7b49
|
3 |
+
size 281938304
|
checkpoint-600/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-800/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b55934126daf4f658ff3ea1c4dda7a922069cdf8a11bae4dc623c5123a1655c3
|
3 |
+
size 5222141436
|
checkpoint-800/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12c8023edd9fa0d3915d111f2fb1ffc8cf3e65dffb763063fafd1c813776eede
|
3 |
+
size 14344
|
checkpoint-800/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20d26e9687ed387160aa99c5f36032f8ef15c2391c97a795e46a4329714467bc
|
3 |
+
size 988
|
checkpoint-800/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92bcc680006bec7a1cd14e8dc1a1b8507ffe1bb293974bdc46a31a9c1e17427f
|
3 |
+
size 1000
|
checkpoint-800/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-800/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc1c3c4d2a33fd6bc3fef84ed1b457822ec8b6a3c04cda693effb8497ced155c
|
3 |
+
size 9988139160
|
checkpoint-800/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34f8bc6961dab75510ce825fe03d8887799fc388620b78c66fa24f8e75e8dacc
|
3 |
+
size 281938304
|
checkpoint-800/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
image_0.png
ADDED
Git LFS Details
|
image_1.png
ADDED
Git LFS Details
|
image_2.png
ADDED
Git LFS Details
|
image_3.png
ADDED
Git LFS Details
|
model_index.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionXLPipeline",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"feature_extractor": [
|
6 |
+
null,
|
7 |
+
null
|
8 |
+
],
|
9 |
+
"force_zeros_for_empty_prompt": true,
|
10 |
+
"image_encoder": [
|
11 |
+
null,
|
12 |
+
null
|
13 |
+
],
|
14 |
+
"scheduler": [
|
15 |
+
"diffusers",
|
16 |
+
"EulerDiscreteScheduler"
|
17 |
+
],
|
18 |
+
"text_encoder": [
|
19 |
+
"transformers",
|
20 |
+
"CLIPTextModel"
|
21 |
+
],
|
22 |
+
"text_encoder_2": [
|
23 |
+
"transformers",
|
24 |
+
"CLIPTextModelWithProjection"
|
25 |
+
],
|
26 |
+
"tokenizer": [
|
27 |
+
"transformers",
|
28 |
+
"CLIPTokenizer"
|
29 |
+
],
|
30 |
+
"tokenizer_2": [
|
31 |
+
"transformers",
|
32 |
+
"CLIPTokenizer"
|
33 |
+
],
|
34 |
+
"unet": [
|
35 |
+
"diffusers",
|
36 |
+
"UNet2DConditionModel"
|
37 |
+
],
|
38 |
+
"vae": [
|
39 |
+
"diffusers",
|
40 |
+
"AutoencoderKL"
|
41 |
+
]
|
42 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "EulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"final_sigmas_type": "zero",
|
9 |
+
"interpolation_type": "linear",
|
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 |
+
"sigma_max": null,
|
16 |
+
"sigma_min": null,
|
17 |
+
"skip_prk_steps": true,
|
18 |
+
"steps_offset": 1,
|
19 |
+
"timestep_spacing": "leading",
|
20 |
+
"timestep_type": "discrete",
|
21 |
+
"trained_betas": null,
|
22 |
+
"use_beta_sigmas": false,
|
23 |
+
"use_exponential_sigmas": false,
|
24 |
+
"use_karras_sigmas": false
|
25 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder",
|
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": 768,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.45.2",
|
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
|