Commit
·
9bdeb5c
1
Parent(s):
b6cc04b
converted using stablediffusionapi.com
Browse files- README.md +66 -0
- model_index.json +1 -1
- safety_checker/config.json +4 -144
- safety_checker/pytorch_model.bin +2 -2
- scheduler/scheduler_config.json +2 -5
- text_encoder/config.json +2 -3
- text_encoder/pytorch_model.bin +2 -2
- tokenizer/tokenizer_config.json +1 -1
- unet/config.json +17 -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 |
+
# AnyPastel API Inference
|
| 12 |
+
|
| 13 |
+

|
| 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 "anypastel"
|
| 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/anypastel)
|
| 23 |
+
|
| 24 |
+
Model link: [View model](https://stablediffusionapi.com/models/anypastel)
|
| 25 |
+
|
| 26 |
+
Credits: [View credits](https://civitai.com/?query=AnyPastel)
|
| 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": "anypastel",
|
| 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**
|
model_index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "StableDiffusionPipeline",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"feature_extractor": [
|
| 5 |
"transformers",
|
| 6 |
"CLIPFeatureExtractor"
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "StableDiffusionPipeline",
|
| 3 |
+
"_diffusers_version": "0.21.2",
|
| 4 |
"feature_extractor": [
|
| 5 |
"transformers",
|
| 6 |
"CLIPFeatureExtractor"
|
safety_checker/config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
|
| 3 |
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
| 4 |
"architectures": [
|
| 5 |
"StableDiffusionSafetyChecker"
|
|
@@ -9,160 +8,21 @@
|
|
| 9 |
"model_type": "clip",
|
| 10 |
"projection_dim": 768,
|
| 11 |
"text_config": {
|
| 12 |
-
"_name_or_path": "",
|
| 13 |
-
"add_cross_attention": false,
|
| 14 |
-
"architectures": null,
|
| 15 |
-
"attention_dropout": 0.0,
|
| 16 |
-
"bad_words_ids": null,
|
| 17 |
-
"begin_suppress_tokens": null,
|
| 18 |
-
"bos_token_id": 0,
|
| 19 |
-
"chunk_size_feed_forward": 0,
|
| 20 |
-
"cross_attention_hidden_size": null,
|
| 21 |
-
"decoder_start_token_id": null,
|
| 22 |
-
"diversity_penalty": 0.0,
|
| 23 |
-
"do_sample": false,
|
| 24 |
"dropout": 0.0,
|
| 25 |
-
"early_stopping": false,
|
| 26 |
-
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
-
"eos_token_id": 2,
|
| 28 |
-
"exponential_decay_length_penalty": null,
|
| 29 |
-
"finetuning_task": null,
|
| 30 |
-
"forced_bos_token_id": null,
|
| 31 |
-
"forced_eos_token_id": null,
|
| 32 |
-
"hidden_act": "quick_gelu",
|
| 33 |
"hidden_size": 768,
|
| 34 |
-
"id2label": {
|
| 35 |
-
"0": "LABEL_0",
|
| 36 |
-
"1": "LABEL_1"
|
| 37 |
-
},
|
| 38 |
-
"initializer_factor": 1.0,
|
| 39 |
-
"initializer_range": 0.02,
|
| 40 |
"intermediate_size": 3072,
|
| 41 |
-
"is_decoder": false,
|
| 42 |
-
"is_encoder_decoder": false,
|
| 43 |
-
"label2id": {
|
| 44 |
-
"LABEL_0": 0,
|
| 45 |
-
"LABEL_1": 1
|
| 46 |
-
},
|
| 47 |
-
"layer_norm_eps": 1e-05,
|
| 48 |
-
"length_penalty": 1.0,
|
| 49 |
-
"max_length": 20,
|
| 50 |
-
"max_position_embeddings": 77,
|
| 51 |
-
"min_length": 0,
|
| 52 |
"model_type": "clip_text_model",
|
| 53 |
-
"
|
| 54 |
-
"num_attention_heads": 12,
|
| 55 |
-
"num_beam_groups": 1,
|
| 56 |
-
"num_beams": 1,
|
| 57 |
-
"num_hidden_layers": 12,
|
| 58 |
-
"num_return_sequences": 1,
|
| 59 |
-
"output_attentions": false,
|
| 60 |
-
"output_hidden_states": false,
|
| 61 |
-
"output_scores": false,
|
| 62 |
-
"pad_token_id": 1,
|
| 63 |
-
"prefix": null,
|
| 64 |
-
"problem_type": null,
|
| 65 |
-
"projection_dim": 512,
|
| 66 |
-
"pruned_heads": {},
|
| 67 |
-
"remove_invalid_values": false,
|
| 68 |
-
"repetition_penalty": 1.0,
|
| 69 |
-
"return_dict": true,
|
| 70 |
-
"return_dict_in_generate": false,
|
| 71 |
-
"sep_token_id": null,
|
| 72 |
-
"suppress_tokens": null,
|
| 73 |
-
"task_specific_params": null,
|
| 74 |
-
"temperature": 1.0,
|
| 75 |
-
"tf_legacy_loss": false,
|
| 76 |
-
"tie_encoder_decoder": false,
|
| 77 |
-
"tie_word_embeddings": true,
|
| 78 |
-
"tokenizer_class": null,
|
| 79 |
-
"top_k": 50,
|
| 80 |
-
"top_p": 1.0,
|
| 81 |
-
"torch_dtype": null,
|
| 82 |
-
"torchscript": false,
|
| 83 |
-
"transformers_version": "4.27.2",
|
| 84 |
-
"typical_p": 1.0,
|
| 85 |
-
"use_bfloat16": false,
|
| 86 |
-
"vocab_size": 49408
|
| 87 |
},
|
| 88 |
-
"torch_dtype": "
|
| 89 |
-
"transformers_version":
|
| 90 |
"vision_config": {
|
| 91 |
-
"_name_or_path": "",
|
| 92 |
-
"add_cross_attention": false,
|
| 93 |
-
"architectures": null,
|
| 94 |
-
"attention_dropout": 0.0,
|
| 95 |
-
"bad_words_ids": null,
|
| 96 |
-
"begin_suppress_tokens": null,
|
| 97 |
-
"bos_token_id": null,
|
| 98 |
-
"chunk_size_feed_forward": 0,
|
| 99 |
-
"cross_attention_hidden_size": null,
|
| 100 |
-
"decoder_start_token_id": null,
|
| 101 |
-
"diversity_penalty": 0.0,
|
| 102 |
-
"do_sample": false,
|
| 103 |
"dropout": 0.0,
|
| 104 |
-
"early_stopping": false,
|
| 105 |
-
"encoder_no_repeat_ngram_size": 0,
|
| 106 |
-
"eos_token_id": null,
|
| 107 |
-
"exponential_decay_length_penalty": null,
|
| 108 |
-
"finetuning_task": null,
|
| 109 |
-
"forced_bos_token_id": null,
|
| 110 |
-
"forced_eos_token_id": null,
|
| 111 |
-
"hidden_act": "quick_gelu",
|
| 112 |
"hidden_size": 1024,
|
| 113 |
-
"id2label": {
|
| 114 |
-
"0": "LABEL_0",
|
| 115 |
-
"1": "LABEL_1"
|
| 116 |
-
},
|
| 117 |
-
"image_size": 224,
|
| 118 |
-
"initializer_factor": 1.0,
|
| 119 |
-
"initializer_range": 0.02,
|
| 120 |
"intermediate_size": 4096,
|
| 121 |
-
"is_decoder": false,
|
| 122 |
-
"is_encoder_decoder": false,
|
| 123 |
-
"label2id": {
|
| 124 |
-
"LABEL_0": 0,
|
| 125 |
-
"LABEL_1": 1
|
| 126 |
-
},
|
| 127 |
-
"layer_norm_eps": 1e-05,
|
| 128 |
-
"length_penalty": 1.0,
|
| 129 |
-
"max_length": 20,
|
| 130 |
-
"min_length": 0,
|
| 131 |
"model_type": "clip_vision_model",
|
| 132 |
-
"no_repeat_ngram_size": 0,
|
| 133 |
"num_attention_heads": 16,
|
| 134 |
-
"num_beam_groups": 1,
|
| 135 |
-
"num_beams": 1,
|
| 136 |
-
"num_channels": 3,
|
| 137 |
"num_hidden_layers": 24,
|
| 138 |
-
"
|
| 139 |
-
"output_attentions": false,
|
| 140 |
-
"output_hidden_states": false,
|
| 141 |
-
"output_scores": false,
|
| 142 |
-
"pad_token_id": null,
|
| 143 |
-
"patch_size": 14,
|
| 144 |
-
"prefix": null,
|
| 145 |
-
"problem_type": null,
|
| 146 |
-
"projection_dim": 512,
|
| 147 |
-
"pruned_heads": {},
|
| 148 |
-
"remove_invalid_values": false,
|
| 149 |
-
"repetition_penalty": 1.0,
|
| 150 |
-
"return_dict": true,
|
| 151 |
-
"return_dict_in_generate": false,
|
| 152 |
-
"sep_token_id": null,
|
| 153 |
-
"suppress_tokens": null,
|
| 154 |
-
"task_specific_params": null,
|
| 155 |
-
"temperature": 1.0,
|
| 156 |
-
"tf_legacy_loss": false,
|
| 157 |
-
"tie_encoder_decoder": false,
|
| 158 |
-
"tie_word_embeddings": true,
|
| 159 |
-
"tokenizer_class": null,
|
| 160 |
-
"top_k": 50,
|
| 161 |
-
"top_p": 1.0,
|
| 162 |
-
"torch_dtype": null,
|
| 163 |
-
"torchscript": false,
|
| 164 |
-
"transformers_version": "4.27.2",
|
| 165 |
-
"typical_p": 1.0,
|
| 166 |
-
"use_bfloat16": false
|
| 167 |
}
|
| 168 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
| 3 |
"architectures": [
|
| 4 |
"StableDiffusionSafetyChecker"
|
|
|
|
| 8 |
"model_type": "clip",
|
| 9 |
"projection_dim": 768,
|
| 10 |
"text_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"intermediate_size": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"model_type": "clip_text_model",
|
| 15 |
+
"num_attention_heads": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
},
|
| 17 |
+
"torch_dtype": "float16",
|
| 18 |
+
"transformers_version": "4.33.1",
|
| 19 |
"vision_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"hidden_size": 1024,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"intermediate_size": 4096,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"model_type": "clip_vision_model",
|
|
|
|
| 24 |
"num_attention_heads": 16,
|
|
|
|
|
|
|
|
|
|
| 25 |
"num_hidden_layers": 24,
|
| 26 |
+
"patch_size": 14
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
}
|
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:e09c5d39c29d798137c7aa6f529bd44abe3616b054740a02d896f0381ca4f4f9
|
| 3 |
+
size 608099578
|
scheduler/scheduler_config.json
CHANGED
|
@@ -1,18 +1,15 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "PNDMScheduler",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"beta_end": 0.012,
|
| 5 |
"beta_schedule": "scaled_linear",
|
| 6 |
"beta_start": 0.00085,
|
| 7 |
"clip_sample": false,
|
| 8 |
-
"clip_sample_range": 1.0,
|
| 9 |
-
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
"num_train_timesteps": 1000,
|
| 11 |
"prediction_type": "epsilon",
|
| 12 |
-
"sample_max_value": 1.0,
|
| 13 |
"set_alpha_to_one": false,
|
| 14 |
"skip_prk_steps": true,
|
| 15 |
"steps_offset": 1,
|
| 16 |
-
"
|
| 17 |
"trained_betas": null
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "PNDMScheduler",
|
| 3 |
+
"_diffusers_version": "0.21.2",
|
| 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 |
+
"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 |
],
|
|
@@ -19,7 +18,7 @@
|
|
| 19 |
"num_hidden_layers": 12,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"projection_dim": 768,
|
| 22 |
-
"torch_dtype": "
|
| 23 |
-
"transformers_version": "4.
|
| 24 |
"vocab_size": 49408
|
| 25 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"CLIPTextModel"
|
| 4 |
],
|
|
|
|
| 18 |
"num_hidden_layers": 12,
|
| 19 |
"pad_token_id": 1,
|
| 20 |
"projection_dim": 768,
|
| 21 |
+
"torch_dtype": "float16",
|
| 22 |
+
"transformers_version": "4.33.1",
|
| 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 sha256:25c87e19853b8ef7eb094b67fb9b47a76af87e949f944ec8be33ddbc3eac38e6
|
| 3 |
+
size 246185562
|
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",
|
|
@@ -20,7 +21,6 @@
|
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 77,
|
| 22 |
"pad_token": "<|endoftext|>",
|
| 23 |
-
"special_tokens_map_file": "./special_tokens_map.json",
|
| 24 |
"tokenizer_class": "CLIPTokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__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",
|
|
|
|
| 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
|
@@ -1,8 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DConditionModel",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"act_fn": "silu",
|
|
|
|
|
|
|
|
|
|
| 5 |
"attention_head_dim": 8,
|
|
|
|
| 6 |
"block_out_channels": [
|
| 7 |
320,
|
| 8 |
640,
|
|
@@ -11,9 +15,11 @@
|
|
| 11 |
],
|
| 12 |
"center_input_sample": false,
|
| 13 |
"class_embed_type": null,
|
|
|
|
| 14 |
"conv_in_kernel": 3,
|
| 15 |
"conv_out_kernel": 3,
|
| 16 |
"cross_attention_dim": 768,
|
|
|
|
| 17 |
"down_block_types": [
|
| 18 |
"CrossAttnDownBlock2D",
|
| 19 |
"CrossAttnDownBlock2D",
|
|
@@ -21,24 +27,34 @@
|
|
| 21 |
"DownBlock2D"
|
| 22 |
],
|
| 23 |
"downsample_padding": 1,
|
|
|
|
| 24 |
"dual_cross_attention": false,
|
|
|
|
|
|
|
| 25 |
"flip_sin_to_cos": true,
|
| 26 |
"freq_shift": 0,
|
| 27 |
"in_channels": 4,
|
| 28 |
"layers_per_block": 2,
|
|
|
|
| 29 |
"mid_block_scale_factor": 1,
|
| 30 |
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 31 |
"norm_eps": 1e-05,
|
| 32 |
"norm_num_groups": 32,
|
|
|
|
| 33 |
"num_class_embeds": null,
|
| 34 |
"only_cross_attention": false,
|
| 35 |
"out_channels": 4,
|
| 36 |
"projection_class_embeddings_input_dim": null,
|
|
|
|
|
|
|
| 37 |
"resnet_time_scale_shift": "default",
|
| 38 |
"sample_size": 64,
|
| 39 |
"time_cond_proj_dim": null,
|
|
|
|
|
|
|
| 40 |
"time_embedding_type": "positional",
|
| 41 |
"timestep_post_act": null,
|
|
|
|
| 42 |
"up_block_types": [
|
| 43 |
"UpBlock2D",
|
| 44 |
"CrossAttnUpBlock2D",
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.21.2",
|
| 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 |
+
"attention_type": "default",
|
| 10 |
"block_out_channels": [
|
| 11 |
320,
|
| 12 |
640,
|
|
|
|
| 15 |
],
|
| 16 |
"center_input_sample": false,
|
| 17 |
"class_embed_type": null,
|
| 18 |
+
"class_embeddings_concat": false,
|
| 19 |
"conv_in_kernel": 3,
|
| 20 |
"conv_out_kernel": 3,
|
| 21 |
"cross_attention_dim": 768,
|
| 22 |
+
"cross_attention_norm": null,
|
| 23 |
"down_block_types": [
|
| 24 |
"CrossAttnDownBlock2D",
|
| 25 |
"CrossAttnDownBlock2D",
|
|
|
|
| 27 |
"DownBlock2D"
|
| 28 |
],
|
| 29 |
"downsample_padding": 1,
|
| 30 |
+
"dropout": 0.0,
|
| 31 |
"dual_cross_attention": false,
|
| 32 |
+
"encoder_hid_dim": null,
|
| 33 |
+
"encoder_hid_dim_type": null,
|
| 34 |
"flip_sin_to_cos": true,
|
| 35 |
"freq_shift": 0,
|
| 36 |
"in_channels": 4,
|
| 37 |
"layers_per_block": 2,
|
| 38 |
+
"mid_block_only_cross_attention": null,
|
| 39 |
"mid_block_scale_factor": 1,
|
| 40 |
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 41 |
"norm_eps": 1e-05,
|
| 42 |
"norm_num_groups": 32,
|
| 43 |
+
"num_attention_heads": null,
|
| 44 |
"num_class_embeds": null,
|
| 45 |
"only_cross_attention": false,
|
| 46 |
"out_channels": 4,
|
| 47 |
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_out_scale_factor": 1.0,
|
| 49 |
+
"resnet_skip_time_act": false,
|
| 50 |
"resnet_time_scale_shift": "default",
|
| 51 |
"sample_size": 64,
|
| 52 |
"time_cond_proj_dim": null,
|
| 53 |
+
"time_embedding_act_fn": null,
|
| 54 |
+
"time_embedding_dim": null,
|
| 55 |
"time_embedding_type": "positional",
|
| 56 |
"timestep_post_act": null,
|
| 57 |
+
"transformer_layers_per_block": 1,
|
| 58 |
"up_block_types": [
|
| 59 |
"UpBlock2D",
|
| 60 |
"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 sha256:4d67faab137e35e86896f3b59f4b84c2ee41699d9158abb62e6327feff1808e5
|
| 3 |
+
size 1719324918
|
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": "0.21.2",
|
| 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:abe1061a3de64f205f56ffe4efdd2ae64cdf338ff8075f7fec065e3835c3eb57
|
| 3 |
+
size 167404866
|