Commit
•
36c182c
0
Parent(s):
Duplicate from glowforge-dev/stable-diffusion-2-1-base-custom
Browse files- .gitattributes +34 -0
- README.md +7 -0
- feature_extractor/preprocessor_config.json +20 -0
- handler.py +51 -0
- model_index.json +33 -0
- requirements.txt +1 -0
- scheduler/scheduler_config.json +14 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- text_encoder/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +34 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +45 -0
- unet/diffusion_pytorch_model.bin +3 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- v2-1_512-ema-pruned.ckpt +3 -0
- v2-1_512-ema-pruned.safetensors +3 -0
- v2-1_512-nonema-pruned.ckpt +3 -0
- v2-1_512-nonema-pruned.safetensors +3 -0
- vae/config.json +29 -0
- vae/diffusion_pytorch_model.bin +3 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
duplicated_from: glowforge-dev/stable-diffusion-2-1-base-custom
|
3 |
+
---
|
4 |
+
# Stable Diffusion v2-1 Custom Implementation
|
5 |
+
Custom implementation of the Stable Diffusion v2.1 base model for Glowforge.
|
6 |
+
|
7 |
+
Forked from the [Stable Diffusion v2.1 base model](https://huggingface.co/stabilityai/stable-diffusion-2-1-base) developed by Robin Rombach and Patrick Esser.
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": 224,
|
3 |
+
"do_center_crop": true,
|
4 |
+
"do_convert_rgb": true,
|
5 |
+
"do_normalize": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
8 |
+
"image_mean": [
|
9 |
+
0.48145466,
|
10 |
+
0.4578275,
|
11 |
+
0.40821073
|
12 |
+
],
|
13 |
+
"image_std": [
|
14 |
+
0.26862954,
|
15 |
+
0.26130258,
|
16 |
+
0.27577711
|
17 |
+
],
|
18 |
+
"resample": 3,
|
19 |
+
"size": 224
|
20 |
+
}
|
handler.py
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from typing import Dict, List, Any
|
2 |
+
import torch
|
3 |
+
from diffusers import StableDiffusionPipeline, EulerAncestralDiscreteScheduler
|
4 |
+
|
5 |
+
# set device
|
6 |
+
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
7 |
+
|
8 |
+
if device.type != 'cuda':
|
9 |
+
raise ValueError("need to run on GPU")
|
10 |
+
|
11 |
+
class EndpointHandler():
|
12 |
+
def __init__(self, path=""):
|
13 |
+
# load the optimized model
|
14 |
+
self.pipe = StableDiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
|
15 |
+
self.pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(self.pipe.scheduler.config)
|
16 |
+
self.pipe = self.pipe.to(device)
|
17 |
+
|
18 |
+
def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
|
19 |
+
"""
|
20 |
+
Args:
|
21 |
+
data (:obj:):
|
22 |
+
includes the input data and the parameters for the inference.
|
23 |
+
Return:
|
24 |
+
A :obj:`dict`:. base64 encoded image
|
25 |
+
"""
|
26 |
+
prompt = data.pop("inputs", data)
|
27 |
+
params = data.pop("parameters", data)
|
28 |
+
|
29 |
+
# hyperparamters
|
30 |
+
num_inference_steps = params.pop("num_inference_steps", 20)
|
31 |
+
guidance_scale = params.pop("guidance_scale", 7.5)
|
32 |
+
negative_prompt = params.pop("negative_prompt", None)
|
33 |
+
height = params.pop("height", None)
|
34 |
+
width = params.pop("width", None)
|
35 |
+
manual_seed = params.pop("manual_seed", -1)
|
36 |
+
|
37 |
+
generator = torch.Generator(device).manual_seed(manual_seed)
|
38 |
+
|
39 |
+
# run inference pipeline
|
40 |
+
out = self.pipe(prompt,
|
41 |
+
generator=generator,
|
42 |
+
num_inference_steps=num_inference_steps,
|
43 |
+
guidance_scale=guidance_scale,
|
44 |
+
num_images_per_prompt=1,
|
45 |
+
negative_prompt=negative_prompt,
|
46 |
+
height=height,
|
47 |
+
width=width
|
48 |
+
)
|
49 |
+
|
50 |
+
# return first generate PIL image
|
51 |
+
return out.images[0]
|
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
+
],
|
8 |
+
"requires_safety_checker": false,
|
9 |
+
"safety_checker": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"PNDMScheduler"
|
16 |
+
],
|
17 |
+
"text_encoder": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTextModel"
|
20 |
+
],
|
21 |
+
"tokenizer": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTokenizer"
|
24 |
+
],
|
25 |
+
"unet": [
|
26 |
+
"diffusers",
|
27 |
+
"UNet2DConditionModel"
|
28 |
+
],
|
29 |
+
"vae": [
|
30 |
+
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
requirements.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
diffusers==0.10.2
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.10.0.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 |
+
"trained_betas": null
|
14 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2",
|
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": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.25.0.dev0",
|
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:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
|
3 |
+
size 1361597018
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3e254d7b61353497ea0be2c4013df4ea8f739ee88cffa0ba58cd085459ed565
|
3 |
+
size 1361671895
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "!",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"do_lower_case": true,
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 77,
|
22 |
+
"name_or_path": "stabilityai/stable-diffusion-2",
|
23 |
+
"pad_token": "<|endoftext|>",
|
24 |
+
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
+
"tokenizer_class": "CLIPTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": [
|
6 |
+
5,
|
7 |
+
10,
|
8 |
+
20,
|
9 |
+
20
|
10 |
+
],
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"cross_attention_dim": 1024,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"flip_sin_to_cos": true,
|
28 |
+
"freq_shift": 0,
|
29 |
+
"in_channels": 4,
|
30 |
+
"layers_per_block": 2,
|
31 |
+
"mid_block_scale_factor": 1,
|
32 |
+
"norm_eps": 1e-05,
|
33 |
+
"norm_num_groups": 32,
|
34 |
+
"num_class_embeds": null,
|
35 |
+
"only_cross_attention": false,
|
36 |
+
"out_channels": 4,
|
37 |
+
"sample_size": 64,
|
38 |
+
"up_block_types": [
|
39 |
+
"UpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D"
|
43 |
+
],
|
44 |
+
"use_linear_projection": true
|
45 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a434f8fdbb51f080ac57a4377281241467c4efc1417b27646ffae989644de60c
|
3 |
+
size 3463913445
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dfae3e5f7d459b50f4b0850ead945972c75bb0e1897628933e169eb43974214
|
3 |
+
size 3463726498
|
v2-1_512-ema-pruned.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88ecb782561455673c4b78d05093494b9c539fc6bfc08f3a9a4a0dd7b0b10f36
|
3 |
+
size 5214865159
|
v2-1_512-ema-pruned.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df955bdf6b682338ea9b55dfc0d8f3475aadf4836e204893d28b82355e0956d2
|
3 |
+
size 5214604494
|
v2-1_512-nonema-pruned.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34dccb9e60d83a4ef963f51e9ff63548323a70024f8679095956d7c403b3ef4a
|
3 |
+
size 5214864585
|
v2-1_512-nonema-pruned.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc4f9fe7528b2ee3de21971fb805bbf74d680bf1ab5b5f9c08379b0397b82a9d
|
3 |
+
size 5214604312
|
vae/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"block_out_channels": [
|
6 |
+
128,
|
7 |
+
256,
|
8 |
+
512,
|
9 |
+
512
|
10 |
+
],
|
11 |
+
"down_block_types": [
|
12 |
+
"DownEncoderBlock2D",
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D"
|
16 |
+
],
|
17 |
+
"in_channels": 3,
|
18 |
+
"latent_channels": 4,
|
19 |
+
"layers_per_block": 2,
|
20 |
+
"norm_num_groups": 32,
|
21 |
+
"out_channels": 3,
|
22 |
+
"sample_size": 768,
|
23 |
+
"up_block_types": [
|
24 |
+
"UpDecoderBlock2D",
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D"
|
28 |
+
]
|
29 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
|
3 |
+
size 334707217
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
|
3 |
+
size 334643276
|