adhikjoshi
commited on
Commit
•
2f78903
1
Parent(s):
d8d6500
converted using stablediffusionapi.com
Browse files- README.md +66 -0
- feature_extractor/preprocessor_config.json +1 -1
- model_index.json +2 -2
- safety_checker/config.json +2 -15
- safety_checker/pytorch_model.bin +2 -2
- scheduler/scheduler_config.json +2 -1
- text_encoder/config.json +1 -2
- text_encoder/pytorch_model.bin +2 -2
- tokenizer/tokenizer_config.json +1 -2
- unet/config.json +21 -1
- unet/diffusion_pytorch_model.bin +2 -2
- vae/config.json +2 -1
- vae/diffusion_pytorch_model.bin +2 -2
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
tags:
|
4 |
+
- stablediffusionapi.com
|
5 |
+
- stable-diffusion-api
|
6 |
+
- text-to-image
|
7 |
+
- ultra-realistic
|
8 |
+
pinned: true
|
9 |
+
---
|
10 |
+
|
11 |
+
# realistic vision API Inference
|
12 |
+
|
13 |
+
![generated from stablediffusionapi.com](https://cdn2.stablediffusionapi.com/generations/8431509861693456971.png)
|
14 |
+
## Get API Key
|
15 |
+
|
16 |
+
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
|
17 |
+
|
18 |
+
Replace Key in below code, change **model_id** to "realistic-vision"
|
19 |
+
|
20 |
+
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
|
21 |
+
|
22 |
+
Try model for free: [Generate Images](https://stablediffusionapi.com/models/realistic-vision)
|
23 |
+
|
24 |
+
Model link: [View model](https://stablediffusionapi.com/models/realistic-vision)
|
25 |
+
|
26 |
+
Credits: [View credits](https://civitai.com/?query=realistic%20vision)
|
27 |
+
|
28 |
+
View all models: [View Models](https://stablediffusionapi.com/models)
|
29 |
+
|
30 |
+
import requests
|
31 |
+
import json
|
32 |
+
|
33 |
+
url = "https://stablediffusionapi.com/api/v4/dreambooth"
|
34 |
+
|
35 |
+
payload = json.dumps({
|
36 |
+
"key": "your_api_key",
|
37 |
+
"model_id": "realistic-vision",
|
38 |
+
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
|
39 |
+
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
|
40 |
+
"width": "512",
|
41 |
+
"height": "512",
|
42 |
+
"samples": "1",
|
43 |
+
"num_inference_steps": "30",
|
44 |
+
"safety_checker": "no",
|
45 |
+
"enhance_prompt": "yes",
|
46 |
+
"seed": None,
|
47 |
+
"guidance_scale": 7.5,
|
48 |
+
"multi_lingual": "no",
|
49 |
+
"panorama": "no",
|
50 |
+
"self_attention": "no",
|
51 |
+
"upscale": "no",
|
52 |
+
"embeddings": "embeddings_model_id",
|
53 |
+
"lora": "lora_model_id",
|
54 |
+
"webhook": None,
|
55 |
+
"track_id": None
|
56 |
+
})
|
57 |
+
|
58 |
+
headers = {
|
59 |
+
'Content-Type': 'application/json'
|
60 |
+
}
|
61 |
+
|
62 |
+
response = requests.request("POST", url, headers=headers, data=payload)
|
63 |
+
|
64 |
+
print(response.text)
|
65 |
+
|
66 |
+
> Use this coupon code to get 25% off **DMGG0RBN**
|
feature_extractor/preprocessor_config.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
0.4578275,
|
15 |
0.40821073
|
16 |
],
|
17 |
-
"image_processor_type": "
|
18 |
"image_std": [
|
19 |
0.26862954,
|
20 |
0.26130258,
|
|
|
14 |
0.4578275,
|
15 |
0.40821073
|
16 |
],
|
17 |
+
"image_processor_type": "CLIPFeatureExtractor",
|
18 |
"image_std": [
|
19 |
0.26862954,
|
20 |
0.26130258,
|
model_index.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
-
"
|
7 |
],
|
8 |
"requires_safety_checker": true,
|
9 |
"safety_checker": [
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.20.0.dev0",
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
"requires_safety_checker": true,
|
9 |
"safety_checker": [
|
safety_checker/config.json
CHANGED
@@ -80,17 +80,11 @@
|
|
80 |
"top_p": 1.0,
|
81 |
"torch_dtype": null,
|
82 |
"torchscript": false,
|
83 |
-
"transformers_version": "4.
|
84 |
"typical_p": 1.0,
|
85 |
"use_bfloat16": false,
|
86 |
"vocab_size": 49408
|
87 |
},
|
88 |
-
"text_config_dict": {
|
89 |
-
"hidden_size": 768,
|
90 |
-
"intermediate_size": 3072,
|
91 |
-
"num_attention_heads": 12,
|
92 |
-
"num_hidden_layers": 12
|
93 |
-
},
|
94 |
"torch_dtype": "float32",
|
95 |
"transformers_version": null,
|
96 |
"vision_config": {
|
@@ -167,15 +161,8 @@
|
|
167 |
"top_p": 1.0,
|
168 |
"torch_dtype": null,
|
169 |
"torchscript": false,
|
170 |
-
"transformers_version": "4.
|
171 |
"typical_p": 1.0,
|
172 |
"use_bfloat16": false
|
173 |
-
},
|
174 |
-
"vision_config_dict": {
|
175 |
-
"hidden_size": 1024,
|
176 |
-
"intermediate_size": 4096,
|
177 |
-
"num_attention_heads": 16,
|
178 |
-
"num_hidden_layers": 24,
|
179 |
-
"patch_size": 14
|
180 |
}
|
181 |
}
|
|
|
80 |
"top_p": 1.0,
|
81 |
"torch_dtype": null,
|
82 |
"torchscript": false,
|
83 |
+
"transformers_version": "4.28.1",
|
84 |
"typical_p": 1.0,
|
85 |
"use_bfloat16": false,
|
86 |
"vocab_size": 49408
|
87 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
"torch_dtype": "float32",
|
89 |
"transformers_version": null,
|
90 |
"vision_config": {
|
|
|
161 |
"top_p": 1.0,
|
162 |
"torch_dtype": null,
|
163 |
"torchscript": false,
|
164 |
+
"transformers_version": "4.28.1",
|
165 |
"typical_p": 1.0,
|
166 |
"use_bfloat16": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
167 |
}
|
168 |
}
|
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 sha256:7ba98d19732abb6b1a90fc030f61430678f9b48f5aae79be5de8e005107c8563
|
3 |
+
size 1216065214
|
scheduler/scheduler_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
@@ -10,5 +10,6 @@
|
|
10 |
"set_alpha_to_one": false,
|
11 |
"skip_prk_steps": true,
|
12 |
"steps_offset": 1,
|
|
|
13 |
"trained_betas": null
|
14 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.20.0.dev0",
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
|
|
10 |
"set_alpha_to_one": false,
|
11 |
"skip_prk_steps": true,
|
12 |
"steps_offset": 1,
|
13 |
+
"timestep_spacing": "leading",
|
14 |
"trained_betas": null
|
15 |
}
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "openai/clip-vit-large-patch14",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -20,6 +19,6 @@
|
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 49408
|
25 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"CLIPTextModel"
|
4 |
],
|
|
|
19 |
"pad_token_id": 1,
|
20 |
"projection_dim": 768,
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.28.1",
|
23 |
"vocab_size": 49408
|
24 |
}
|
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:d5e8fe0598d0f88c3d88ae443c2060a879bc7bef007b75c9770462605dfe5e3f
|
3 |
+
size 492307486
|
tokenizer/tokenizer_config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
|
|
11 |
"do_lower_case": true,
|
12 |
"eos_token": {
|
13 |
"__type": "AddedToken",
|
@@ -19,9 +20,7 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
-
"name_or_path": "openai/clip-vit-large-patch14",
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
-
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
26 |
"unk_token": {
|
27 |
"__type": "AddedToken",
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
"do_lower_case": true,
|
13 |
"eos_token": {
|
14 |
"__type": "AddedToken",
|
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 77,
|
|
|
23 |
"pad_token": "<|endoftext|>",
|
|
|
24 |
"tokenizer_class": "CLIPTokenizer",
|
25 |
"unk_token": {
|
26 |
"__type": "AddedToken",
|
unet/config.json
CHANGED
@@ -1,7 +1,10 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
|
|
|
|
|
|
5 |
"attention_head_dim": 8,
|
6 |
"block_out_channels": [
|
7 |
320,
|
@@ -11,7 +14,11 @@
|
|
11 |
],
|
12 |
"center_input_sample": false,
|
13 |
"class_embed_type": null,
|
|
|
|
|
|
|
14 |
"cross_attention_dim": 768,
|
|
|
15 |
"down_block_types": [
|
16 |
"CrossAttnDownBlock2D",
|
17 |
"CrossAttnDownBlock2D",
|
@@ -20,19 +27,32 @@
|
|
20 |
],
|
21 |
"downsample_padding": 1,
|
22 |
"dual_cross_attention": false,
|
|
|
|
|
23 |
"flip_sin_to_cos": true,
|
24 |
"freq_shift": 0,
|
25 |
"in_channels": 4,
|
26 |
"layers_per_block": 2,
|
|
|
27 |
"mid_block_scale_factor": 1,
|
28 |
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
29 |
"norm_eps": 1e-05,
|
30 |
"norm_num_groups": 32,
|
|
|
31 |
"num_class_embeds": null,
|
32 |
"only_cross_attention": false,
|
33 |
"out_channels": 4,
|
|
|
|
|
|
|
34 |
"resnet_time_scale_shift": "default",
|
35 |
"sample_size": 64,
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
"up_block_types": [
|
37 |
"UpBlock2D",
|
38 |
"CrossAttnUpBlock2D",
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.20.0.dev0",
|
4 |
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": null,
|
8 |
"attention_head_dim": 8,
|
9 |
"block_out_channels": [
|
10 |
320,
|
|
|
14 |
],
|
15 |
"center_input_sample": false,
|
16 |
"class_embed_type": null,
|
17 |
+
"class_embeddings_concat": false,
|
18 |
+
"conv_in_kernel": 3,
|
19 |
+
"conv_out_kernel": 3,
|
20 |
"cross_attention_dim": 768,
|
21 |
+
"cross_attention_norm": null,
|
22 |
"down_block_types": [
|
23 |
"CrossAttnDownBlock2D",
|
24 |
"CrossAttnDownBlock2D",
|
|
|
27 |
],
|
28 |
"downsample_padding": 1,
|
29 |
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"encoder_hid_dim_type": null,
|
32 |
"flip_sin_to_cos": true,
|
33 |
"freq_shift": 0,
|
34 |
"in_channels": 4,
|
35 |
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
"mid_block_scale_factor": 1,
|
38 |
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
"norm_eps": 1e-05,
|
40 |
"norm_num_groups": 32,
|
41 |
+
"num_attention_heads": null,
|
42 |
"num_class_embeds": null,
|
43 |
"only_cross_attention": false,
|
44 |
"out_channels": 4,
|
45 |
+
"projection_class_embeddings_input_dim": null,
|
46 |
+
"resnet_out_scale_factor": 1.0,
|
47 |
+
"resnet_skip_time_act": false,
|
48 |
"resnet_time_scale_shift": "default",
|
49 |
"sample_size": 64,
|
50 |
+
"time_cond_proj_dim": null,
|
51 |
+
"time_embedding_act_fn": null,
|
52 |
+
"time_embedding_dim": null,
|
53 |
+
"time_embedding_type": "positional",
|
54 |
+
"timestep_post_act": null,
|
55 |
+
"transformer_layers_per_block": 1,
|
56 |
"up_block_types": [
|
57 |
"UpBlock2D",
|
58 |
"CrossAttnUpBlock2D",
|
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 sha256:5235af98664d312048812a22ebf58ef50c1289a73eeb0cd2d628ec9758314644
|
3 |
+
size 3438366838
|
vae/config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
@@ -14,6 +14,7 @@
|
|
14 |
"DownEncoderBlock2D",
|
15 |
"DownEncoderBlock2D"
|
16 |
],
|
|
|
17 |
"in_channels": 3,
|
18 |
"latent_channels": 4,
|
19 |
"layers_per_block": 2,
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.20.0.dev0",
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
|
|
14 |
"DownEncoderBlock2D",
|
15 |
"DownEncoderBlock2D"
|
16 |
],
|
17 |
+
"force_upcast": true,
|
18 |
"in_channels": 3,
|
19 |
"latent_channels": 4,
|
20 |
"layers_per_block": 2,
|
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 sha256:0efa237bb22bfbb62a755d1b492123dffcb622323671f14856f6d85817bfa33c
|
3 |
+
size 334712578
|