patrickvonplaten
commited on
Commit
•
3beed0b
1
Parent(s):
245f52e
add fp16
Browse files- safety_checker/config.json +3 -3
- safety_checker/pytorch_model.bin +2 -2
- text_encoder/config.json +2 -2
- text_encoder/pytorch_model.bin +2 -2
- tokenizer/tokenizer_config.json +1 -1
- unet/config.json +1 -0
- unet/diffusion_pytorch_model.bin +2 -2
- v1-5-pruned-emaonly.ckpt +0 -3
- v1-inference.yaml +0 -70
- vae/config.json +1 -0
- vae/diffusion_pytorch_model.bin +2 -2
safety_checker/config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"_commit_hash":
|
3 |
-
"_name_or_path": "
|
4 |
"architectures": [
|
5 |
"StableDiffusionSafetyChecker"
|
6 |
],
|
@@ -88,7 +88,7 @@
|
|
88 |
"num_attention_heads": 12,
|
89 |
"num_hidden_layers": 12
|
90 |
},
|
91 |
-
"torch_dtype": "
|
92 |
"transformers_version": null,
|
93 |
"vision_config": {
|
94 |
"_name_or_path": "",
|
1 |
{
|
2 |
+
"_commit_hash": null,
|
3 |
+
"_name_or_path": "/home/patrick/stable-diffusion-v1-5/safety_checker",
|
4 |
"architectures": [
|
5 |
"StableDiffusionSafetyChecker"
|
6 |
],
|
88 |
"num_attention_heads": 12,
|
89 |
"num_hidden_layers": 12
|
90 |
},
|
91 |
+
"torch_dtype": "float16",
|
92 |
"transformers_version": null,
|
93 |
"vision_config": {
|
94 |
"_name_or_path": "",
|
safety_checker/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d37ca6e57ace94e4c2f03ed0f67b6dc83e1ef1160892074917aa68b28e2afc1
|
3 |
+
size 608098599
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -19,7 +19,7 @@
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
-
"torch_dtype": "
|
23 |
"transformers_version": "4.22.0.dev0",
|
24 |
"vocab_size": 49408
|
25 |
}
|
1 |
{
|
2 |
+
"_name_or_path": "/home/patrick/stable-diffusion-v1-5/text_encoder",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float16",
|
23 |
"transformers_version": "4.22.0.dev0",
|
24 |
"vocab_size": 49408
|
25 |
}
|
text_encoder/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88bd85efb0f84e70521633f578715afb2873db4f2615fdfb1f66e99934715865
|
3 |
+
size 246184375
|
tokenizer/tokenizer_config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
-
"name_or_path": "
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
+
"name_or_path": "/home/patrick/stable-diffusion-v1-5/tokenizer",
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
unet/config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.6.0",
|
|
|
4 |
"act_fn": "silu",
|
5 |
"attention_head_dim": 8,
|
6 |
"block_out_channels": [
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.6.0",
|
4 |
+
"_name_or_path": "/home/patrick/stable-diffusion-v1-5/unet",
|
5 |
"act_fn": "silu",
|
6 |
"attention_head_dim": 8,
|
7 |
"block_out_channels": [
|
unet/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5019a4fbb455dd9b75192afc3ecf8a8ec875e83812fd51029d2e19277edddebc
|
3 |
+
size 1719312805
|
v1-5-pruned-emaonly.ckpt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516
|
3 |
-
size 4265380512
|
|
|
|
|
|
v1-inference.yaml
DELETED
@@ -1,70 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
base_learning_rate: 1.0e-04
|
3 |
-
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
4 |
-
params:
|
5 |
-
linear_start: 0.00085
|
6 |
-
linear_end: 0.0120
|
7 |
-
num_timesteps_cond: 1
|
8 |
-
log_every_t: 200
|
9 |
-
timesteps: 1000
|
10 |
-
first_stage_key: "jpg"
|
11 |
-
cond_stage_key: "txt"
|
12 |
-
image_size: 64
|
13 |
-
channels: 4
|
14 |
-
cond_stage_trainable: false # Note: different from the one we trained before
|
15 |
-
conditioning_key: crossattn
|
16 |
-
monitor: val/loss_simple_ema
|
17 |
-
scale_factor: 0.18215
|
18 |
-
use_ema: False
|
19 |
-
|
20 |
-
scheduler_config: # 10000 warmup steps
|
21 |
-
target: ldm.lr_scheduler.LambdaLinearScheduler
|
22 |
-
params:
|
23 |
-
warm_up_steps: [ 10000 ]
|
24 |
-
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
25 |
-
f_start: [ 1.e-6 ]
|
26 |
-
f_max: [ 1. ]
|
27 |
-
f_min: [ 1. ]
|
28 |
-
|
29 |
-
unet_config:
|
30 |
-
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
31 |
-
params:
|
32 |
-
image_size: 32 # unused
|
33 |
-
in_channels: 4
|
34 |
-
out_channels: 4
|
35 |
-
model_channels: 320
|
36 |
-
attention_resolutions: [ 4, 2, 1 ]
|
37 |
-
num_res_blocks: 2
|
38 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
39 |
-
num_heads: 8
|
40 |
-
use_spatial_transformer: True
|
41 |
-
transformer_depth: 1
|
42 |
-
context_dim: 768
|
43 |
-
use_checkpoint: True
|
44 |
-
legacy: False
|
45 |
-
|
46 |
-
first_stage_config:
|
47 |
-
target: ldm.models.autoencoder.AutoencoderKL
|
48 |
-
params:
|
49 |
-
embed_dim: 4
|
50 |
-
monitor: val/rec_loss
|
51 |
-
ddconfig:
|
52 |
-
double_z: true
|
53 |
-
z_channels: 4
|
54 |
-
resolution: 256
|
55 |
-
in_channels: 3
|
56 |
-
out_ch: 3
|
57 |
-
ch: 128
|
58 |
-
ch_mult:
|
59 |
-
- 1
|
60 |
-
- 2
|
61 |
-
- 4
|
62 |
-
- 4
|
63 |
-
num_res_blocks: 2
|
64 |
-
attn_resolutions: []
|
65 |
-
dropout: 0.0
|
66 |
-
lossconfig:
|
67 |
-
target: torch.nn.Identity
|
68 |
-
|
69 |
-
cond_stage_config:
|
70 |
-
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vae/config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
"_diffusers_version": "0.6.0",
|
|
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
"_diffusers_version": "0.6.0",
|
4 |
+
"_name_or_path": "/home/patrick/stable-diffusion-v1-5/vae",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
vae/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51c8904bc921e1e6f354b5fa8e99a1c82ead2f0540114de21557b8abfbb24ad0
|
3 |
+
size 167399505
|