tejasghutukade
commited on
Commit
•
6866051
1
Parent(s):
9820b13
End of training
Browse files- checkpoint-150/optimizer.bin +3 -0
- checkpoint-150/random_states_0.pkl +3 -0
- checkpoint-150/scaler.pt +3 -0
- checkpoint-150/scheduler.bin +3 -0
- checkpoint-150/unet/config.json +68 -0
- checkpoint-150/unet/diffusion_pytorch_model.safetensors +3 -0
- model_index.json +3 -3
- safety_checker/config.json +1 -1
- scheduler/scheduler_config.json +10 -2
- text_encoder/config.json +1 -1
- unet/config.json +1 -1
- unet/diffusion_pytorch_model.safetensors +1 -1
- vae/config.json +1 -1
checkpoint-150/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb0f3d71543ad22e36a7a9ff3f05dda531febdebbfacfc3fa4e2bd5c567800be
|
3 |
+
size 6876842324
|
checkpoint-150/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2922e1bb2fd82c447a5901c995b75dd81ef438f61aba8237b6bc471c34002867
|
3 |
+
size 14408
|
checkpoint-150/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da800fd5ac660f36778294f9df633c4f039b5f7bde42ca6a92dea5ac7d9666b1
|
3 |
+
size 988
|
checkpoint-150/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6fb14b70c8f76bdadcc6cb1a604ecdb92553773524139f13977c57b9b5c1d04
|
3 |
+
size 1000
|
checkpoint-150/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "timbrooks/instruct-pix2pix",
|
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": 8,
|
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 |
+
}
|
checkpoint-150/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31aea63ecd0cbd28fa9cafbce96cd5815d25d75c2554d1c57a9eb6fabdd9a012
|
3 |
+
size 3438213624
|
model_index.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionInstructPix2PixPipeline",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
-
"_name_or_path": "
|
5 |
"feature_extractor": [
|
6 |
"transformers",
|
7 |
"CLIPImageProcessor"
|
@@ -10,14 +10,14 @@
|
|
10 |
null,
|
11 |
null
|
12 |
],
|
13 |
-
"requires_safety_checker":
|
14 |
"safety_checker": [
|
15 |
"stable_diffusion",
|
16 |
"StableDiffusionSafetyChecker"
|
17 |
],
|
18 |
"scheduler": [
|
19 |
"diffusers",
|
20 |
-
"
|
21 |
],
|
22 |
"text_encoder": [
|
23 |
"transformers",
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionInstructPix2PixPipeline",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "timbrooks/instruct-pix2pix",
|
5 |
"feature_extractor": [
|
6 |
"transformers",
|
7 |
"CLIPImageProcessor"
|
|
|
10 |
null,
|
11 |
null
|
12 |
],
|
13 |
+
"requires_safety_checker": false,
|
14 |
"safety_checker": [
|
15 |
"stable_diffusion",
|
16 |
"StableDiffusionSafetyChecker"
|
17 |
],
|
18 |
"scheduler": [
|
19 |
"diffusers",
|
20 |
+
"EulerAncestralDiscreteScheduler"
|
21 |
],
|
22 |
"text_encoder": [
|
23 |
"transformers",
|
safety_checker/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/root/.cache/huggingface/hub/models--
|
3 |
"architectures": [
|
4 |
"StableDiffusionSafetyChecker"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/huggingface/hub/models--timbrooks--instruct-pix2pix/snapshots/31519b5cb02a7fd89b906d88731cd4d6a7bbf88d/safety_checker",
|
3 |
"architectures": [
|
4 |
"StableDiffusionSafetyChecker"
|
5 |
],
|
scheduler/scheduler_config.json
CHANGED
@@ -1,15 +1,23 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
"_diffusers_version": "0.30.0.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 |
-
"
|
|
|
14 |
"trained_betas": null
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "EulerAncestralDiscreteScheduler",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"algorithm_type": "dpmsolver++",
|
5 |
"beta_end": 0.012,
|
6 |
"beta_schedule": "scaled_linear",
|
7 |
"beta_start": 0.00085,
|
8 |
"clip_sample": false,
|
9 |
+
"dynamic_thresholding_ratio": 0.995,
|
10 |
+
"lower_order_final": true,
|
11 |
"num_train_timesteps": 1000,
|
12 |
"prediction_type": "epsilon",
|
13 |
+
"rescale_betas_zero_snr": false,
|
14 |
+
"sample_max_value": 1.0,
|
15 |
"set_alpha_to_one": false,
|
16 |
"skip_prk_steps": true,
|
17 |
+
"solver_order": 2,
|
18 |
+
"solver_type": "midpoint",
|
19 |
"steps_offset": 1,
|
20 |
+
"thresholding": false,
|
21 |
+
"timestep_spacing": "linspace",
|
22 |
"trained_betas": null
|
23 |
}
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "timbrooks/instruct-pix2pix",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
unet/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
-
"_name_or_path": "
|
5 |
"act_fn": "silu",
|
6 |
"addition_embed_type": null,
|
7 |
"addition_embed_type_num_heads": 64,
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "timbrooks/instruct-pix2pix",
|
5 |
"act_fn": "silu",
|
6 |
"addition_embed_type": null,
|
7 |
"addition_embed_type_num_heads": 64,
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438213624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31aea63ecd0cbd28fa9cafbce96cd5815d25d75c2554d1c57a9eb6fabdd9a012
|
3 |
size 3438213624
|
vae/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
-
"_name_or_path": "
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "timbrooks/instruct-pix2pix",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|