Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/Untitled-checkpoint.ipynb +6 -0
- Untitled.ipynb +51 -0
- checkpoint-1000/unet/config.json +68 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1000/unet_ema/.ipynb_checkpoints/config-checkpoint.json +75 -0
- checkpoint-1000/unet_ema/config.json +75 -0
- checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1500/unet/config.json +68 -0
- checkpoint-1500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1500/unet_ema/config.json +75 -0
- checkpoint-1500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2000/unet/config.json +68 -0
- checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/unet_ema/config.json +75 -0
- checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2500/unet/config.json +68 -0
- checkpoint-2500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2500/unet_ema/config.json +75 -0
- checkpoint-2500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/unet/config.json +68 -0
- checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/unet_ema/config.json +75 -0
- checkpoint-3000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3500/optimizer.bin +3 -0
- checkpoint-3500/random_states_0.pkl +3 -0
- checkpoint-3500/scaler.pt +3 -0
- checkpoint-3500/scheduler.bin +3 -0
- checkpoint-3500/unet/config.json +68 -0
- checkpoint-3500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3500/unet_ema/config.json +75 -0
- checkpoint-3500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-4000/unet/config.json +68 -0
- checkpoint-4000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-4000/unet_ema/config.json +75 -0
- checkpoint-4000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-500/unet/config.json +68 -0
- checkpoint-500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-500/unet_ema/config.json +75 -0
- checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- logs/text2image-fine-tune/1714098128.6234279/events.out.tfevents.1714098128.d5f9278d1682.584.1 +3 -0
- logs/text2image-fine-tune/1714098128.6248305/hparams.yml +51 -0
- logs/text2image-fine-tune/events.out.tfevents.1714098128.d5f9278d1682.584.0 +3 -0
.ipynb_checkpoints/Untitled-checkpoint.ipynb
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [],
|
3 |
+
"metadata": {},
|
4 |
+
"nbformat": 4,
|
5 |
+
"nbformat_minor": 5
|
6 |
+
}
|
Untitled.ipynb
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"id": "7a4f9213-ac23-4f92-af20-74db0bd4f74a",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [
|
9 |
+
{
|
10 |
+
"ename": "ModuleNotFoundError",
|
11 |
+
"evalue": "No module named 'huggingface_hub'",
|
12 |
+
"output_type": "error",
|
13 |
+
"traceback": [
|
14 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
15 |
+
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
16 |
+
"Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mhuggingface_hub\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m HfApi, logging\n\u001b[1;32m 3\u001b[0m logging\u001b[38;5;241m.\u001b[39mset_verbosity_debug()\n\u001b[1;32m 4\u001b[0m hf \u001b[38;5;241m=\u001b[39m HfApi()\n",
|
17 |
+
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'huggingface_hub'"
|
18 |
+
]
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"source": [
|
22 |
+
"from huggingface_hub import HfApi, logging\n",
|
23 |
+
"\n",
|
24 |
+
"logging.set_verbosity_debug()\n",
|
25 |
+
"hf = HfApi()\n",
|
26 |
+
"hf.upload_file(path_or_fileobj=\".\", path_in_repo=\".\", repo_id=\"mrtuandao/pokemon-finetune\", repo_type=\"model\")"
|
27 |
+
]
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"metadata": {
|
31 |
+
"kernelspec": {
|
32 |
+
"display_name": "Python 3 (ipykernel)",
|
33 |
+
"language": "python",
|
34 |
+
"name": "python3"
|
35 |
+
},
|
36 |
+
"language_info": {
|
37 |
+
"codemirror_mode": {
|
38 |
+
"name": "ipython",
|
39 |
+
"version": 3
|
40 |
+
},
|
41 |
+
"file_extension": ".py",
|
42 |
+
"mimetype": "text/x-python",
|
43 |
+
"name": "python",
|
44 |
+
"nbconvert_exporter": "python",
|
45 |
+
"pygments_lexer": "ipython3",
|
46 |
+
"version": "3.10.12"
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"nbformat": 4,
|
50 |
+
"nbformat_minor": 5
|
51 |
+
}
|
checkpoint-1000/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 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad105bf382f6736d73cb79745e756bd4ed6cb928ef6ac543e601edbb684679d7
|
3 |
+
size 3438167536
|
checkpoint-1000/unet_ema/.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 1000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-1000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 1000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e12a55ab4ea2802d9f514878c27f97b72368a0f937313f28610e06999cc693e3
|
3 |
+
size 3438167536
|
checkpoint-1500/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 |
+
}
|
checkpoint-1500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb04a3aa1e180f1f8515dddafa271d094d3deac31ce3bb71b9a17225c402180
|
3 |
+
size 3438167536
|
checkpoint-1500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 1500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-1500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e186a1fc90dbdffd00cb9c467c57fc26e4519f6865304a8ba4b7203882e47dc
|
3 |
+
size 3438167536
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75eca8492f36696e90521531ad9710dade0a4bca7fe6e5a95f4d7fd3d1636974
|
3 |
+
size 6876750164
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52ab13ab5801004e1fc5d57b8ddd17128c2fb3f8bc4e4fedbe4317baaa6ba84e
|
3 |
+
size 14344
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c50a9cebe5d66d453d25b140738bff479749ac03e0a43597d8776bc22f6ed0c
|
3 |
+
size 988
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a7fe0a2983de695c44ba167520d4ce1ca01157e36e90498bee8c9d8e4b61fc
|
3 |
+
size 1000
|
checkpoint-2000/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 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e08d7aa2d6ead4f56371759ede370af909812d313ac6ab3fa02c119029e7162
|
3 |
+
size 3438167536
|
checkpoint-2000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 2000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dbfca58eec1dccc80b6f7f3c5289d98e8df826e31fbc08cb46e10f023462caf
|
3 |
+
size 3438167536
|
checkpoint-2500/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 |
+
}
|
checkpoint-2500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dd29b591d8f0bf5c7191529ceea98b5239ee65596321e6bc44aa57aef916cfd
|
3 |
+
size 3438167536
|
checkpoint-2500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 2500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-2500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69a9a578c4fdce249b87c87611ce422a01ac9b71c05e56ec9558db2a14b6089f
|
3 |
+
size 3438167536
|
checkpoint-3000/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 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bb0bc9b953706bd512ca870d6c1d05d744609169b4434f9af545dc8d9655568
|
3 |
+
size 3438167536
|
checkpoint-3000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 3000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-3000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc3265fff6659025dd07f02aa5f48b11221d8ea8160918b592399ccd20982b1c
|
3 |
+
size 3438167536
|
checkpoint-3500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc94379d5ba0d9ba5e43f797406c57c0df7cc50f556ad1bb1af0a1eb35b198b8
|
3 |
+
size 6876750164
|
checkpoint-3500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:332c65a4a7a064b01edaf31abe5241b4af9c4977cdcaa725d5b13f85f0b99dde
|
3 |
+
size 14344
|
checkpoint-3500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d25c9e5c384ba91142c829ef5432ebc4ae7d8c71f3de723046dd3aa202e08a2
|
3 |
+
size 988
|
checkpoint-3500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6802221f6347629ca3a6e377a3bbcf1d2a6c0b7ef7e83794854e08587237ffd4
|
3 |
+
size 1000
|
checkpoint-3500/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 |
+
}
|
checkpoint-3500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed9223e6c0c56465b0b3dbd75e935858bbc683b3b3029974742e026d7297e06d
|
3 |
+
size 3438167536
|
checkpoint-3500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 3500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-3500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:642b0c309df57745353c29df00bdec4fd538c2d80d24ab74f9d4522c88788487
|
3 |
+
size 3438167536
|
checkpoint-4000/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 |
+
}
|
checkpoint-4000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5be180fac430348bbeb9c1404557e49bf52153c861011972217fea158c72cdcc
|
3 |
+
size 1914830848
|
checkpoint-4000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 4000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-4000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:988856f05f36d803a4e8c4a1d6cfcb600d3b2920f8ca0e5282abb287bc2186e3
|
3 |
+
size 3438167536
|
checkpoint-500/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 |
+
}
|
checkpoint-500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b633c7c121171004189c145660e77d57df26d25fe387bc9aa9907a450020b7b
|
3 |
+
size 3438167536
|
checkpoint-500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:300d8af69b01bfec4e78bc18e6cc7e988a17d733358a779137d3f3f6fc2c7566
|
3 |
+
size 3438167536
|
logs/text2image-fine-tune/1714098128.6234279/events.out.tfevents.1714098128.d5f9278d1682.584.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d65cdd43c4e6b1a558d138d56594530e5a76a4ab7a50cdfeb48acffbc3ef195
|
3 |
+
size 2267
|
logs/text2image-fine-tune/1714098128.6248305/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: en_text
|
8 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: svjack/pokemon-blip-captions-en-zh
|
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: 5000
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
non_ema_revision: null
|
32 |
+
num_train_epochs: 24
|
33 |
+
output_dir: sd-pokemon-model
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
36 |
+
push_to_hub: false
|
37 |
+
random_flip: true
|
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.1714098128.d5f9278d1682.584.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:715084a5879aa9024ac516735f224519dca4c8fd664769bb78a537930e483373
|
3 |
+
size 195961
|