hassanblend commited on
Commit
25811db
1 Parent(s): fcfca67

Upload 18 files

Browse files
app.py ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
2
+ import gradio as gr
3
+ import torch
4
+ from PIL import Image
5
+
6
+ model_id = 'hassanblend/HassanBlend1.5'
7
+ prefix = ''
8
+
9
+ scheduler = DPMSolverMultistepScheduler(
10
+ beta_start=0.00085,
11
+ beta_end=0.012,
12
+ beta_schedule="scaled_linear",
13
+ num_train_timesteps=1000,
14
+ trained_betas=None,
15
+ predict_epsilon=True,
16
+ thresholding=False,
17
+ algorithm_type="dpmsolver++",
18
+ solver_type="midpoint",
19
+ lower_order_final=True,
20
+ )
21
+
22
+ pipe = StableDiffusionPipeline.from_pretrained(
23
+ model_id,
24
+ torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
25
+ scheduler=scheduler)
26
+
27
+ pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
28
+ model_id,
29
+ torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
30
+ scheduler=scheduler)
31
+
32
+ if torch.cuda.is_available():
33
+ pipe = pipe.to("cuda")
34
+ pipe_i2i = pipe_i2i.to("cuda")
35
+
36
+ def error_str(error, title="Error"):
37
+ return f"""#### {title}
38
+ {error}""" if error else ""
39
+
40
+ def inference(prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt="", auto_prefix=True):
41
+
42
+ generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
43
+ prompt = f"{prefix} {prompt}" if auto_prefix else prompt
44
+
45
+ try:
46
+ if img is not None:
47
+ return img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator), None
48
+ else:
49
+ return txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator), None
50
+ except Exception as e:
51
+ return None, error_str(e)
52
+
53
+ def txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator):
54
+
55
+ result = pipe(
56
+ prompt,
57
+ negative_prompt = neg_prompt,
58
+ num_inference_steps = int(steps),
59
+ guidance_scale = guidance,
60
+ width = width,
61
+ height = height,
62
+ generator = generator)
63
+
64
+ return replace_nsfw_images(result)
65
+
66
+ def img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator):
67
+
68
+ ratio = min(height / img.height, width / img.width)
69
+ img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
70
+ result = pipe_i2i(
71
+ prompt,
72
+ negative_prompt = neg_prompt,
73
+ init_image = img,
74
+ num_inference_steps = int(steps),
75
+ strength = strength,
76
+ guidance_scale = guidance,
77
+ width = width,
78
+ height = height,
79
+ generator = generator)
80
+
81
+ return replace_nsfw_images(result)
82
+
83
+ def replace_nsfw_images(results):
84
+
85
+ for i in range(len(results.images)):
86
+ if results.nsfw_content_detected[i]:
87
+ results.images[i] = Image.open("nsfw.png")
88
+ return results.images[0]
89
+
90
+ css = """.main-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.main-div div h1{font-weight:900;margin-bottom:7px}.main-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
91
+ """
92
+ with gr.Blocks(css=css) as demo:
93
+ gr.HTML(
94
+ f"""
95
+ <div class="main-div">
96
+ <div>
97
+ <h1>Hassanblend1.5</h1>
98
+ </div>
99
+ <p>
100
+ Demo for <a href="https://huggingface.co/hassanblend/HassanBlend1.5">Hassanblend1.5</a> Stable Diffusion model.<br>
101
+ Add the following tokens to your prompts for the model to work properly: <b></b>.
102
+ </p>
103
+ Running on <b>{"GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"}</b>
104
+ </div>
105
+ """
106
+ )
107
+ with gr.Row():
108
+
109
+ with gr.Column(scale=55):
110
+ with gr.Group():
111
+ with gr.Row():
112
+ prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder=f"{prefix} [your prompt]").style(container=False)
113
+ generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
114
+
115
+ image_out = gr.Image(height=512)
116
+ error_output = gr.Markdown()
117
+
118
+ with gr.Column(scale=45):
119
+ with gr.Tab("Options"):
120
+ with gr.Group():
121
+ neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
122
+ auto_prefix = gr.Checkbox(label="Prefix styling tokens automatically ()", value=True)
123
+
124
+ with gr.Row():
125
+ guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
126
+ steps = gr.Slider(label="Steps", value=25, minimum=2, maximum=75, step=1)
127
+
128
+ with gr.Row():
129
+ width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
130
+ height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)
131
+
132
+ seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)
133
+
134
+ with gr.Tab("Image to image"):
135
+ with gr.Group():
136
+ image = gr.Image(label="Image", height=256, tool="editor", type="pil")
137
+ strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
138
+
139
+ auto_prefix.change(lambda x: gr.update(placeholder=f"{prefix} [your prompt]" if x else "[Your prompt]"), inputs=auto_prefix, outputs=prompt, queue=False)
140
+
141
+ inputs = [prompt, guidance, steps, width, height, seed, image, strength, neg_prompt, auto_prefix]
142
+ outputs = [image_out, error_output]
143
+ prompt.submit(inference, inputs=inputs, outputs=outputs)
144
+ generate.click(inference, inputs=inputs, outputs=outputs)
145
+
146
+ gr.HTML("""
147
+ <div style="border-top: 1px solid #303030;">
148
+ <br>
149
+ <p>This space was created using <a href="https://huggingface.co/spaces/anzorq/sd-space-creator">SD Space Creator</a>.</p>
150
+ </div>
151
+ """)
152
+
153
+ demo.queue(concurrency_count=1)
154
+ demo.launch()
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
+ }
model_index.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.7.2",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "safety_checker": [
9
+ "stable_diffusion",
10
+ "StableDiffusionSafetyChecker"
11
+ ],
12
+ "scheduler": [
13
+ "diffusers",
14
+ "PNDMScheduler"
15
+ ],
16
+ "text_encoder": [
17
+ "transformers",
18
+ "CLIPTextModel"
19
+ ],
20
+ "tokenizer": [
21
+ "transformers",
22
+ "CLIPTokenizer"
23
+ ],
24
+ "unet": [
25
+ "diffusers",
26
+ "UNet2DConditionModel"
27
+ ],
28
+ "vae": [
29
+ "diffusers",
30
+ "AutoencoderKL"
31
+ ]
32
+ }
pipeline.py ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ class PreTrainedPipeline():
2
+ def __init__(self, path=""):
3
+ # IMPLEMENT_THIS
4
+ # Preload all the elements you are going to need at inference.
5
+ # For instance your model, processors, tokenizer that might be needed.
6
+ # This function is only called once, so do all the heavy processing I/O here"""
7
+ raise NotImplementedError(
8
+ "Please implement PreTrainedPipeline __init__ function"
9
+ )
10
+
11
+ def __call__(self, inputs: str):
12
+ """
13
+ Args:
14
+ inputs (:obj:`str`):
15
+ a string containing some text
16
+ Return:
17
+ A :obj:`PIL.Image` with the raw image representation as PIL.
18
+ """
19
+ # IMPLEMENT_THIS
20
+ raise NotImplementedError(
21
+ "Please implement PreTrainedPipeline __call__ function"
22
+ )
requirements.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ --extra-index-url https://download.pytorch.org/whl/cu113
2
+ torch
3
+ diffusers
4
+ transformers
5
+ accelerate
6
+ ftfy
safety_checker/config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
3
+ "_name_or_path": "CompVis/stable-diffusion-safety-checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
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
+ "no_repeat_ngram_size": 0,
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
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.24.0",
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "vocab_size": 49408
86
+ },
87
+ "text_config_dict": {
88
+ "hidden_size": 768,
89
+ "intermediate_size": 3072,
90
+ "num_attention_heads": 12,
91
+ "num_hidden_layers": 12
92
+ },
93
+ "torch_dtype": "float32",
94
+ "transformers_version": null,
95
+ "vision_config": {
96
+ "_name_or_path": "",
97
+ "add_cross_attention": false,
98
+ "architectures": null,
99
+ "attention_dropout": 0.0,
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "dropout": 0.0,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "quick_gelu",
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 224,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-05,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "clip_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 24,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.24.0",
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false
171
+ },
172
+ "vision_config_dict": {
173
+ "hidden_size": 1024,
174
+ "intermediate_size": 4096,
175
+ "num_attention_heads": 16,
176
+ "num_hidden_layers": 24,
177
+ "patch_size": 14
178
+ }
179
+ }
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.7.2",
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
+ "set_alpha_to_one": false,
10
+ "skip_prk_steps": true,
11
+ "steps_offset": 1,
12
+ "trained_betas": null
13
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
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": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.24.0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b9e059a2af92f8bdff755be76dcaa30b7473346541aadee05707a601cc616e
3
+ size 492307041
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": "<|endoftext|>",
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": "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",
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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.7.2",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": 8,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "center_input_sample": false,
13
+ "cross_attention_dim": 768,
14
+ "down_block_types": [
15
+ "CrossAttnDownBlock2D",
16
+ "CrossAttnDownBlock2D",
17
+ "CrossAttnDownBlock2D",
18
+ "DownBlock2D"
19
+ ],
20
+ "downsample_padding": 1,
21
+ "flip_sin_to_cos": true,
22
+ "freq_shift": 0,
23
+ "in_channels": 4,
24
+ "layers_per_block": 2,
25
+ "mid_block_scale_factor": 1,
26
+ "norm_eps": 1e-05,
27
+ "norm_num_groups": 32,
28
+ "out_channels": 4,
29
+ "sample_size": 64,
30
+ "up_block_types": [
31
+ "UpBlock2D",
32
+ "CrossAttnUpBlock2D",
33
+ "CrossAttnUpBlock2D",
34
+ "CrossAttnUpBlock2D"
35
+ ]
36
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9579b198d3f04fc72f2b0423f72f581848abf37fb620da0ea5eee214ddfc0b5
3
+ size 3438366373
vae/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.7.2",
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": 256,
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 sha256:8b35db0323c11c073d28be039e178331d36efe1fd40f4a9d2dd68b74b62040b4
3
+ size 334711857