Hugging Face's logo

iitolstykh
/
VIBE-Image-Edit

Image-to-Image
Diffusers
Safetensors
Sana
English
VIBESanaEditingPipeline
image-editing
text-guided-editing
diffusion
qwen-vl
multimodal
Model card Files
xet
Community
2
iitolstykh commited on
Commit
2dc6555
·
verified ·
1 Parent(s): 887bc70

Upload 16 files

Browse files
Files changed (16) hide show
  1. scheduler/scheduler_config.json +30 -0
  2. text_encoder/config.json +63 -0
  3. text_encoder/generation_config.json +14 -0
  4. text_encoder/model.safetensors +3 -0
  5. tokenizer/chat_template.json +4 -0
  6. tokenizer/merges.txt +0 -0
  7. tokenizer/preprocessor_config.json +21 -0
  8. tokenizer/tokenizer.json +0 -0
  9. tokenizer/tokenizer_config.json +239 -0
  10. tokenizer/video_preprocessor_config.json +21 -0
  11. tokenizer/vocab.json +0 -0
  12. transformer/config.json +27 -0
  13. transformer/diffusion_pytorch_model-00001-of-00001.safetensors +3 -0
  14. transformer/diffusion_pytorch_model.safetensors.index.json +546 -0
  15. vae/config.json +89 -0
  16. vae/diffusion_pytorch_model.safetensors +3 -0
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.33.1",
4
+ "algorithm_type": "dpmsolver++",
5
+ "beta_end": 0.02,
6
+ "beta_schedule": "linear",
7
+ "beta_start": 0.0001,
8
+ "dynamic_thresholding_ratio": 0.995,
9
+ "euler_at_final": false,
10
+ "final_sigmas_type": "zero",
11
+ "flow_shift": 3.0,
12
+ "lambda_min_clipped": -Infinity,
13
+ "lower_order_final": true,
14
+ "num_train_timesteps": 1000,
15
+ "prediction_type": "flow_prediction",
16
+ "rescale_betas_zero_snr": false,
17
+ "sample_max_value": 1.0,
18
+ "solver_order": 2,
19
+ "solver_type": "midpoint",
20
+ "steps_offset": 0,
21
+ "thresholding": false,
22
+ "timestep_spacing": "linspace",
23
+ "trained_betas": null,
24
+ "use_beta_sigmas": false,
25
+ "use_exponential_sigmas": false,
26
+ "use_flow_sigmas": true,
27
+ "use_karras_sigmas": false,
28
+ "use_lu_lambdas": false,
29
+ "variance_type": null
30
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 151655,
6
+ "model_type": "qwen3_vl",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 151643,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 151645,
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 6144,
18
+ "max_position_embeddings": 262144,
19
+ "model_type": "qwen3_vl_text",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 28,
22
+ "num_key_value_heads": 8,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": {
25
+ "mrope_interleaved": true,
26
+ "mrope_section": [
27
+ 24,
28
+ 20,
29
+ 20
30
+ ],
31
+ "rope_type": "default"
32
+ },
33
+ "rope_theta": 5000000,
34
+ "tie_word_embeddings": true,
35
+ "use_cache": true,
36
+ "vocab_size": 151936
37
+ },
38
+ "tie_word_embeddings": true,
39
+ "transformers_version": "4.57.1",
40
+ "video_token_id": 151656,
41
+ "vision_config": {
42
+ "deepstack_visual_indexes": [
43
+ 5,
44
+ 11,
45
+ 17
46
+ ],
47
+ "depth": 24,
48
+ "hidden_act": "gelu_pytorch_tanh",
49
+ "hidden_size": 1024,
50
+ "in_channels": 3,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "model_type": "qwen3_vl",
54
+ "num_heads": 16,
55
+ "num_position_embeddings": 2304,
56
+ "out_hidden_size": 2048,
57
+ "patch_size": 16,
58
+ "spatial_merge_size": 2,
59
+ "temporal_patch_size": 2
60
+ },
61
+ "vision_end_token_id": 151653,
62
+ "vision_start_token_id": 151652
63
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "pad_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "top_p": 0.8,
10
+ "top_k": 20,
11
+ "temperature": 0.7,
12
+ "repetition_penalty": 1.0,
13
+ "transformers_version": "4.56.0"
14
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de1838c87a5349b016c26a1c3f7d2bc400a3d485f95ef39a7059ffd734977a0
3
+ size 4255140312
tokenizer/chat_template.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
3
+ }
4
+
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
tokenizer/video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "VIBESanaEditingModel",
3
+ "_diffusers_version": "0.33.1",
4
+ "attention_bias": false,
5
+ "attention_head_dim": 32,
6
+ "caption_channels": 2304,
7
+ "cross_attention_dim": 2240,
8
+ "cross_attention_head_dim": 112,
9
+ "dropout": 0.0,
10
+ "guidance_embeds": false,
11
+ "in_channels": 64,
12
+ "interpolation_scale": null,
13
+ "mlp_ratio": 2.5,
14
+ "norm_elementwise_affine": false,
15
+ "norm_eps": 1e-06,
16
+ "num_attention_heads": 70,
17
+ "num_cross_attention_heads": 20,
18
+ "num_layers": 20,
19
+ "out_channels": 32,
20
+ "patch_size": 1,
21
+ "qk_norm": "rms_norm_across_heads",
22
+ "edit_head_input_dim": 2048,
23
+ "edit_head_stacks_num": 4,
24
+ "num_meta_queries": 224,
25
+ "meta_queries_dim": 2048,
26
+ "input_condition_type": "channel_cat"
27
+ }
transformer/diffusion_pytorch_model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac81406ec9f673a120695f83db41745f1b7b0e8a0b1f45a8de66aa420fc52c54
3
+ size 3765399232
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,546 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 3765336896
4
+ },
5
+ "weight_map": {
6
+ "caption_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
7
+ "caption_projection.linear_1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
8
+ "caption_projection.linear_1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
9
+ "caption_projection.linear_2.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
10
+ "caption_projection.linear_2.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
11
+ "edit_head.attn_blocks.0.attn.in_proj_bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
12
+ "edit_head.attn_blocks.0.attn.in_proj_weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
13
+ "edit_head.attn_blocks.0.attn.out_proj.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
14
+ "edit_head.attn_blocks.0.attn.out_proj.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
15
+ "edit_head.attn_blocks.0.input_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
16
+ "edit_head.attn_blocks.0.input_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
17
+ "edit_head.attn_blocks.0.mlp.fc1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
18
+ "edit_head.attn_blocks.0.mlp.fc1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
19
+ "edit_head.attn_blocks.0.mlp.fc2.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
20
+ "edit_head.attn_blocks.0.mlp.fc2.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
21
+ "edit_head.attn_blocks.0.mlp.fc3.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
22
+ "edit_head.attn_blocks.0.mlp.fc3.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
23
+ "edit_head.attn_blocks.0.output_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
24
+ "edit_head.attn_blocks.0.output_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
25
+ "edit_head.attn_blocks.1.attn.in_proj_bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
26
+ "edit_head.attn_blocks.1.attn.in_proj_weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
27
+ "edit_head.attn_blocks.1.attn.out_proj.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
28
+ "edit_head.attn_blocks.1.attn.out_proj.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
29
+ "edit_head.attn_blocks.1.input_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
30
+ "edit_head.attn_blocks.1.input_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
31
+ "edit_head.attn_blocks.1.mlp.fc1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
32
+ "edit_head.attn_blocks.1.mlp.fc1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
33
+ "edit_head.attn_blocks.1.mlp.fc2.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
34
+ "edit_head.attn_blocks.1.mlp.fc2.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
35
+ "edit_head.attn_blocks.1.mlp.fc3.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
36
+ "edit_head.attn_blocks.1.mlp.fc3.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
37
+ "edit_head.attn_blocks.1.output_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
38
+ "edit_head.attn_blocks.1.output_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
39
+ "edit_head.attn_blocks.2.attn.in_proj_bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
40
+ "edit_head.attn_blocks.2.attn.in_proj_weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
41
+ "edit_head.attn_blocks.2.attn.out_proj.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
42
+ "edit_head.attn_blocks.2.attn.out_proj.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
43
+ "edit_head.attn_blocks.2.input_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
44
+ "edit_head.attn_blocks.2.input_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
45
+ "edit_head.attn_blocks.2.mlp.fc1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
46
+ "edit_head.attn_blocks.2.mlp.fc1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
47
+ "edit_head.attn_blocks.2.mlp.fc2.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
48
+ "edit_head.attn_blocks.2.mlp.fc2.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
49
+ "edit_head.attn_blocks.2.mlp.fc3.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
50
+ "edit_head.attn_blocks.2.mlp.fc3.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
51
+ "edit_head.attn_blocks.2.output_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
52
+ "edit_head.attn_blocks.2.output_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
53
+ "edit_head.attn_blocks.3.attn.in_proj_bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
54
+ "edit_head.attn_blocks.3.attn.in_proj_weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
55
+ "edit_head.attn_blocks.3.attn.out_proj.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
56
+ "edit_head.attn_blocks.3.attn.out_proj.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
57
+ "edit_head.attn_blocks.3.input_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
58
+ "edit_head.attn_blocks.3.input_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
59
+ "edit_head.attn_blocks.3.mlp.fc1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
60
+ "edit_head.attn_blocks.3.mlp.fc1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
61
+ "edit_head.attn_blocks.3.mlp.fc2.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
62
+ "edit_head.attn_blocks.3.mlp.fc2.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
63
+ "edit_head.attn_blocks.3.mlp.fc3.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
64
+ "edit_head.attn_blocks.3.mlp.fc3.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
65
+ "edit_head.attn_blocks.3.output_norm.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
66
+ "edit_head.attn_blocks.3.output_norm.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
67
+ "edit_head.input_proj.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
68
+ "edit_head.input_proj.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
69
+ "edit_head.output_proj.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
70
+ "edit_head.output_proj.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
71
+ "edit_head.output_proj.1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
72
+ "edit_head.output_proj.1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
73
+ "meta_queries": "diffusion_pytorch_model-00001-of-00001.safetensors",
74
+ "patch_embed.proj.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
75
+ "patch_embed.proj.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
76
+ "proj_out.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
77
+ "proj_out.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
78
+ "scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
79
+ "time_embed.emb.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
80
+ "time_embed.emb.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
81
+ "time_embed.emb.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
82
+ "time_embed.emb.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
83
+ "time_embed.linear.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
84
+ "time_embed.linear.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
85
+ "transformer_blocks.0.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
86
+ "transformer_blocks.0.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
87
+ "transformer_blocks.0.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
88
+ "transformer_blocks.0.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
89
+ "transformer_blocks.0.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
90
+ "transformer_blocks.0.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
91
+ "transformer_blocks.0.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
92
+ "transformer_blocks.0.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
93
+ "transformer_blocks.0.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
94
+ "transformer_blocks.0.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
95
+ "transformer_blocks.0.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
96
+ "transformer_blocks.0.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
97
+ "transformer_blocks.0.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
98
+ "transformer_blocks.0.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
99
+ "transformer_blocks.0.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
100
+ "transformer_blocks.0.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
101
+ "transformer_blocks.0.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
102
+ "transformer_blocks.0.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
103
+ "transformer_blocks.0.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
104
+ "transformer_blocks.0.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
105
+ "transformer_blocks.0.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
106
+ "transformer_blocks.0.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
107
+ "transformer_blocks.0.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
108
+ "transformer_blocks.1.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
109
+ "transformer_blocks.1.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
110
+ "transformer_blocks.1.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
111
+ "transformer_blocks.1.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
112
+ "transformer_blocks.1.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
113
+ "transformer_blocks.1.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
114
+ "transformer_blocks.1.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
115
+ "transformer_blocks.1.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
116
+ "transformer_blocks.1.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
117
+ "transformer_blocks.1.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
118
+ "transformer_blocks.1.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
119
+ "transformer_blocks.1.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
120
+ "transformer_blocks.1.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
121
+ "transformer_blocks.1.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
122
+ "transformer_blocks.1.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
123
+ "transformer_blocks.1.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
124
+ "transformer_blocks.1.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
125
+ "transformer_blocks.1.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
126
+ "transformer_blocks.1.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
127
+ "transformer_blocks.1.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
128
+ "transformer_blocks.1.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
129
+ "transformer_blocks.1.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
130
+ "transformer_blocks.1.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
131
+ "transformer_blocks.10.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
132
+ "transformer_blocks.10.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
133
+ "transformer_blocks.10.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
134
+ "transformer_blocks.10.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
135
+ "transformer_blocks.10.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
136
+ "transformer_blocks.10.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
137
+ "transformer_blocks.10.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
138
+ "transformer_blocks.10.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
139
+ "transformer_blocks.10.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
140
+ "transformer_blocks.10.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
141
+ "transformer_blocks.10.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
142
+ "transformer_blocks.10.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
143
+ "transformer_blocks.10.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
144
+ "transformer_blocks.10.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
145
+ "transformer_blocks.10.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
146
+ "transformer_blocks.10.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
147
+ "transformer_blocks.10.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
148
+ "transformer_blocks.10.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
149
+ "transformer_blocks.10.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
150
+ "transformer_blocks.10.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
151
+ "transformer_blocks.10.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
152
+ "transformer_blocks.10.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
153
+ "transformer_blocks.10.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
154
+ "transformer_blocks.11.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
155
+ "transformer_blocks.11.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
156
+ "transformer_blocks.11.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
157
+ "transformer_blocks.11.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
158
+ "transformer_blocks.11.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
159
+ "transformer_blocks.11.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
160
+ "transformer_blocks.11.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
161
+ "transformer_blocks.11.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
162
+ "transformer_blocks.11.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
163
+ "transformer_blocks.11.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
164
+ "transformer_blocks.11.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
165
+ "transformer_blocks.11.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
166
+ "transformer_blocks.11.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
167
+ "transformer_blocks.11.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
168
+ "transformer_blocks.11.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
169
+ "transformer_blocks.11.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
170
+ "transformer_blocks.11.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
171
+ "transformer_blocks.11.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
172
+ "transformer_blocks.11.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
173
+ "transformer_blocks.11.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
174
+ "transformer_blocks.11.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
175
+ "transformer_blocks.11.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
176
+ "transformer_blocks.11.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
177
+ "transformer_blocks.12.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
178
+ "transformer_blocks.12.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
179
+ "transformer_blocks.12.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
180
+ "transformer_blocks.12.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
181
+ "transformer_blocks.12.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
182
+ "transformer_blocks.12.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
183
+ "transformer_blocks.12.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
184
+ "transformer_blocks.12.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
185
+ "transformer_blocks.12.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
186
+ "transformer_blocks.12.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
187
+ "transformer_blocks.12.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
188
+ "transformer_blocks.12.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
189
+ "transformer_blocks.12.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
190
+ "transformer_blocks.12.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
191
+ "transformer_blocks.12.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
192
+ "transformer_blocks.12.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
193
+ "transformer_blocks.12.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
194
+ "transformer_blocks.12.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
195
+ "transformer_blocks.12.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
196
+ "transformer_blocks.12.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
197
+ "transformer_blocks.12.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
198
+ "transformer_blocks.12.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
199
+ "transformer_blocks.12.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
200
+ "transformer_blocks.13.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
201
+ "transformer_blocks.13.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
202
+ "transformer_blocks.13.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
203
+ "transformer_blocks.13.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
204
+ "transformer_blocks.13.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
205
+ "transformer_blocks.13.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
206
+ "transformer_blocks.13.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
207
+ "transformer_blocks.13.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
208
+ "transformer_blocks.13.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
209
+ "transformer_blocks.13.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
210
+ "transformer_blocks.13.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
211
+ "transformer_blocks.13.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
212
+ "transformer_blocks.13.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
213
+ "transformer_blocks.13.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
214
+ "transformer_blocks.13.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
215
+ "transformer_blocks.13.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
216
+ "transformer_blocks.13.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
217
+ "transformer_blocks.13.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
218
+ "transformer_blocks.13.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
219
+ "transformer_blocks.13.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
220
+ "transformer_blocks.13.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
221
+ "transformer_blocks.13.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
222
+ "transformer_blocks.13.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
223
+ "transformer_blocks.14.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
224
+ "transformer_blocks.14.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
225
+ "transformer_blocks.14.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
226
+ "transformer_blocks.14.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
227
+ "transformer_blocks.14.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
228
+ "transformer_blocks.14.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
229
+ "transformer_blocks.14.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
230
+ "transformer_blocks.14.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
231
+ "transformer_blocks.14.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
232
+ "transformer_blocks.14.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
233
+ "transformer_blocks.14.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
234
+ "transformer_blocks.14.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
235
+ "transformer_blocks.14.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
236
+ "transformer_blocks.14.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
237
+ "transformer_blocks.14.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
238
+ "transformer_blocks.14.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
239
+ "transformer_blocks.14.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
240
+ "transformer_blocks.14.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
241
+ "transformer_blocks.14.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
242
+ "transformer_blocks.14.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
243
+ "transformer_blocks.14.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
244
+ "transformer_blocks.14.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
245
+ "transformer_blocks.14.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
246
+ "transformer_blocks.15.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
247
+ "transformer_blocks.15.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
248
+ "transformer_blocks.15.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
249
+ "transformer_blocks.15.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
250
+ "transformer_blocks.15.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
251
+ "transformer_blocks.15.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
252
+ "transformer_blocks.15.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
253
+ "transformer_blocks.15.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
254
+ "transformer_blocks.15.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
255
+ "transformer_blocks.15.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
256
+ "transformer_blocks.15.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
257
+ "transformer_blocks.15.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
258
+ "transformer_blocks.15.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
259
+ "transformer_blocks.15.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
260
+ "transformer_blocks.15.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
261
+ "transformer_blocks.15.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
262
+ "transformer_blocks.15.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
263
+ "transformer_blocks.15.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
264
+ "transformer_blocks.15.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
265
+ "transformer_blocks.15.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
266
+ "transformer_blocks.15.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
267
+ "transformer_blocks.15.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
268
+ "transformer_blocks.15.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
269
+ "transformer_blocks.16.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
270
+ "transformer_blocks.16.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
271
+ "transformer_blocks.16.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
272
+ "transformer_blocks.16.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
273
+ "transformer_blocks.16.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
274
+ "transformer_blocks.16.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
275
+ "transformer_blocks.16.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
276
+ "transformer_blocks.16.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
277
+ "transformer_blocks.16.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
278
+ "transformer_blocks.16.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
279
+ "transformer_blocks.16.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
280
+ "transformer_blocks.16.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
281
+ "transformer_blocks.16.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
282
+ "transformer_blocks.16.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
283
+ "transformer_blocks.16.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
284
+ "transformer_blocks.16.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
285
+ "transformer_blocks.16.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
286
+ "transformer_blocks.16.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
287
+ "transformer_blocks.16.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
288
+ "transformer_blocks.16.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
289
+ "transformer_blocks.16.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
290
+ "transformer_blocks.16.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
291
+ "transformer_blocks.16.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
292
+ "transformer_blocks.17.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
293
+ "transformer_blocks.17.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
294
+ "transformer_blocks.17.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
295
+ "transformer_blocks.17.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
296
+ "transformer_blocks.17.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
297
+ "transformer_blocks.17.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
298
+ "transformer_blocks.17.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
299
+ "transformer_blocks.17.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
300
+ "transformer_blocks.17.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
301
+ "transformer_blocks.17.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
302
+ "transformer_blocks.17.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
303
+ "transformer_blocks.17.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
304
+ "transformer_blocks.17.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
305
+ "transformer_blocks.17.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
306
+ "transformer_blocks.17.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
307
+ "transformer_blocks.17.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
308
+ "transformer_blocks.17.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
309
+ "transformer_blocks.17.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
310
+ "transformer_blocks.17.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
311
+ "transformer_blocks.17.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
312
+ "transformer_blocks.17.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
313
+ "transformer_blocks.17.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
314
+ "transformer_blocks.17.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
315
+ "transformer_blocks.18.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
316
+ "transformer_blocks.18.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
317
+ "transformer_blocks.18.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
318
+ "transformer_blocks.18.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
319
+ "transformer_blocks.18.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
320
+ "transformer_blocks.18.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
321
+ "transformer_blocks.18.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
322
+ "transformer_blocks.18.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
323
+ "transformer_blocks.18.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
324
+ "transformer_blocks.18.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
325
+ "transformer_blocks.18.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
326
+ "transformer_blocks.18.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
327
+ "transformer_blocks.18.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
328
+ "transformer_blocks.18.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
329
+ "transformer_blocks.18.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
330
+ "transformer_blocks.18.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
331
+ "transformer_blocks.18.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
332
+ "transformer_blocks.18.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
333
+ "transformer_blocks.18.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
334
+ "transformer_blocks.18.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
335
+ "transformer_blocks.18.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
336
+ "transformer_blocks.18.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
337
+ "transformer_blocks.18.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
338
+ "transformer_blocks.19.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
339
+ "transformer_blocks.19.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
340
+ "transformer_blocks.19.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
341
+ "transformer_blocks.19.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
342
+ "transformer_blocks.19.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
343
+ "transformer_blocks.19.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
344
+ "transformer_blocks.19.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
345
+ "transformer_blocks.19.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
346
+ "transformer_blocks.19.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
347
+ "transformer_blocks.19.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
348
+ "transformer_blocks.19.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
349
+ "transformer_blocks.19.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
350
+ "transformer_blocks.19.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
351
+ "transformer_blocks.19.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
352
+ "transformer_blocks.19.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
353
+ "transformer_blocks.19.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
354
+ "transformer_blocks.19.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
355
+ "transformer_blocks.19.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
356
+ "transformer_blocks.19.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
357
+ "transformer_blocks.19.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
358
+ "transformer_blocks.19.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
359
+ "transformer_blocks.19.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
360
+ "transformer_blocks.19.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
361
+ "transformer_blocks.2.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
362
+ "transformer_blocks.2.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
363
+ "transformer_blocks.2.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
364
+ "transformer_blocks.2.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
365
+ "transformer_blocks.2.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
366
+ "transformer_blocks.2.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
367
+ "transformer_blocks.2.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
368
+ "transformer_blocks.2.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
369
+ "transformer_blocks.2.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
370
+ "transformer_blocks.2.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
371
+ "transformer_blocks.2.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
372
+ "transformer_blocks.2.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
373
+ "transformer_blocks.2.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
374
+ "transformer_blocks.2.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
375
+ "transformer_blocks.2.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
376
+ "transformer_blocks.2.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
377
+ "transformer_blocks.2.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
378
+ "transformer_blocks.2.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
379
+ "transformer_blocks.2.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
380
+ "transformer_blocks.2.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
381
+ "transformer_blocks.2.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
382
+ "transformer_blocks.2.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
383
+ "transformer_blocks.2.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
384
+ "transformer_blocks.3.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
385
+ "transformer_blocks.3.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
386
+ "transformer_blocks.3.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
387
+ "transformer_blocks.3.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
388
+ "transformer_blocks.3.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
389
+ "transformer_blocks.3.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
390
+ "transformer_blocks.3.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
391
+ "transformer_blocks.3.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
392
+ "transformer_blocks.3.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
393
+ "transformer_blocks.3.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
394
+ "transformer_blocks.3.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
395
+ "transformer_blocks.3.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
396
+ "transformer_blocks.3.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
397
+ "transformer_blocks.3.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
398
+ "transformer_blocks.3.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
399
+ "transformer_blocks.3.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
400
+ "transformer_blocks.3.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
401
+ "transformer_blocks.3.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
402
+ "transformer_blocks.3.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
403
+ "transformer_blocks.3.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
404
+ "transformer_blocks.3.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
405
+ "transformer_blocks.3.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
406
+ "transformer_blocks.3.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
407
+ "transformer_blocks.4.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
408
+ "transformer_blocks.4.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
409
+ "transformer_blocks.4.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
410
+ "transformer_blocks.4.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
411
+ "transformer_blocks.4.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
412
+ "transformer_blocks.4.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
413
+ "transformer_blocks.4.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
414
+ "transformer_blocks.4.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
415
+ "transformer_blocks.4.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
416
+ "transformer_blocks.4.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
417
+ "transformer_blocks.4.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
418
+ "transformer_blocks.4.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
419
+ "transformer_blocks.4.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
420
+ "transformer_blocks.4.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
421
+ "transformer_blocks.4.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
422
+ "transformer_blocks.4.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
423
+ "transformer_blocks.4.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
424
+ "transformer_blocks.4.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
425
+ "transformer_blocks.4.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
426
+ "transformer_blocks.4.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
427
+ "transformer_blocks.4.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
428
+ "transformer_blocks.4.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
429
+ "transformer_blocks.4.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
430
+ "transformer_blocks.5.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
431
+ "transformer_blocks.5.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
432
+ "transformer_blocks.5.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
433
+ "transformer_blocks.5.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
434
+ "transformer_blocks.5.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
435
+ "transformer_blocks.5.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
436
+ "transformer_blocks.5.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
437
+ "transformer_blocks.5.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
438
+ "transformer_blocks.5.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
439
+ "transformer_blocks.5.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
440
+ "transformer_blocks.5.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
441
+ "transformer_blocks.5.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
442
+ "transformer_blocks.5.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
443
+ "transformer_blocks.5.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
444
+ "transformer_blocks.5.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
445
+ "transformer_blocks.5.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
446
+ "transformer_blocks.5.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
447
+ "transformer_blocks.5.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
448
+ "transformer_blocks.5.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
449
+ "transformer_blocks.5.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
450
+ "transformer_blocks.5.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
451
+ "transformer_blocks.5.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
452
+ "transformer_blocks.5.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
453
+ "transformer_blocks.6.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
454
+ "transformer_blocks.6.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
455
+ "transformer_blocks.6.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
456
+ "transformer_blocks.6.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
457
+ "transformer_blocks.6.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
458
+ "transformer_blocks.6.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
459
+ "transformer_blocks.6.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
460
+ "transformer_blocks.6.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
461
+ "transformer_blocks.6.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
462
+ "transformer_blocks.6.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
463
+ "transformer_blocks.6.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
464
+ "transformer_blocks.6.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
465
+ "transformer_blocks.6.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
466
+ "transformer_blocks.6.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
467
+ "transformer_blocks.6.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
468
+ "transformer_blocks.6.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
469
+ "transformer_blocks.6.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
470
+ "transformer_blocks.6.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
471
+ "transformer_blocks.6.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
472
+ "transformer_blocks.6.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
473
+ "transformer_blocks.6.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
474
+ "transformer_blocks.6.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
475
+ "transformer_blocks.6.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
476
+ "transformer_blocks.7.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
477
+ "transformer_blocks.7.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
478
+ "transformer_blocks.7.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
479
+ "transformer_blocks.7.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
480
+ "transformer_blocks.7.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
481
+ "transformer_blocks.7.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
482
+ "transformer_blocks.7.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
483
+ "transformer_blocks.7.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
484
+ "transformer_blocks.7.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
485
+ "transformer_blocks.7.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
486
+ "transformer_blocks.7.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
487
+ "transformer_blocks.7.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
488
+ "transformer_blocks.7.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
489
+ "transformer_blocks.7.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
490
+ "transformer_blocks.7.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
491
+ "transformer_blocks.7.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
492
+ "transformer_blocks.7.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
493
+ "transformer_blocks.7.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
494
+ "transformer_blocks.7.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
495
+ "transformer_blocks.7.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
496
+ "transformer_blocks.7.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
497
+ "transformer_blocks.7.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
498
+ "transformer_blocks.7.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
499
+ "transformer_blocks.8.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
500
+ "transformer_blocks.8.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
501
+ "transformer_blocks.8.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
502
+ "transformer_blocks.8.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
503
+ "transformer_blocks.8.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
504
+ "transformer_blocks.8.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
505
+ "transformer_blocks.8.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
506
+ "transformer_blocks.8.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
507
+ "transformer_blocks.8.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
508
+ "transformer_blocks.8.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
509
+ "transformer_blocks.8.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
510
+ "transformer_blocks.8.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
511
+ "transformer_blocks.8.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
512
+ "transformer_blocks.8.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
513
+ "transformer_blocks.8.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
514
+ "transformer_blocks.8.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
515
+ "transformer_blocks.8.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
516
+ "transformer_blocks.8.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
517
+ "transformer_blocks.8.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
518
+ "transformer_blocks.8.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
519
+ "transformer_blocks.8.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
520
+ "transformer_blocks.8.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
521
+ "transformer_blocks.8.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors",
522
+ "transformer_blocks.9.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
523
+ "transformer_blocks.9.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
524
+ "transformer_blocks.9.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
525
+ "transformer_blocks.9.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
526
+ "transformer_blocks.9.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
527
+ "transformer_blocks.9.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
528
+ "transformer_blocks.9.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
529
+ "transformer_blocks.9.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
530
+ "transformer_blocks.9.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
531
+ "transformer_blocks.9.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
532
+ "transformer_blocks.9.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
533
+ "transformer_blocks.9.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
534
+ "transformer_blocks.9.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
535
+ "transformer_blocks.9.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
536
+ "transformer_blocks.9.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
537
+ "transformer_blocks.9.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
538
+ "transformer_blocks.9.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
539
+ "transformer_blocks.9.ff.conv_depth.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
540
+ "transformer_blocks.9.ff.conv_depth.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
541
+ "transformer_blocks.9.ff.conv_inverted.bias": "diffusion_pytorch_model-00001-of-00001.safetensors",
542
+ "transformer_blocks.9.ff.conv_inverted.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
543
+ "transformer_blocks.9.ff.conv_point.weight": "diffusion_pytorch_model-00001-of-00001.safetensors",
544
+ "transformer_blocks.9.scale_shift_table": "diffusion_pytorch_model-00001-of-00001.safetensors"
545
+ }
546
+ }
vae/config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderDC",
3
+ "_diffusers_version": "0.33.1",
4
+ "_name_or_path": "mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers",
5
+ "attention_head_dim": 32,
6
+ "decoder_act_fns": "silu",
7
+ "decoder_block_out_channels": [
8
+ 128,
9
+ 256,
10
+ 512,
11
+ 512,
12
+ 1024,
13
+ 1024
14
+ ],
15
+ "decoder_block_types": [
16
+ "ResBlock",
17
+ "ResBlock",
18
+ "ResBlock",
19
+ "EfficientViTBlock",
20
+ "EfficientViTBlock",
21
+ "EfficientViTBlock"
22
+ ],
23
+ "decoder_layers_per_block": [
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 3
30
+ ],
31
+ "decoder_norm_types": "rms_norm",
32
+ "decoder_qkv_multiscales": [
33
+ [],
34
+ [],
35
+ [],
36
+ [
37
+ 5
38
+ ],
39
+ [
40
+ 5
41
+ ],
42
+ [
43
+ 5
44
+ ]
45
+ ],
46
+ "downsample_block_type": "Conv",
47
+ "encoder_block_out_channels": [
48
+ 128,
49
+ 256,
50
+ 512,
51
+ 512,
52
+ 1024,
53
+ 1024
54
+ ],
55
+ "encoder_block_types": [
56
+ "ResBlock",
57
+ "ResBlock",
58
+ "ResBlock",
59
+ "EfficientViTBlock",
60
+ "EfficientViTBlock",
61
+ "EfficientViTBlock"
62
+ ],
63
+ "encoder_layers_per_block": [
64
+ 2,
65
+ 2,
66
+ 2,
67
+ 3,
68
+ 3,
69
+ 3
70
+ ],
71
+ "encoder_qkv_multiscales": [
72
+ [],
73
+ [],
74
+ [],
75
+ [
76
+ 5
77
+ ],
78
+ [
79
+ 5
80
+ ],
81
+ [
82
+ 5
83
+ ]
84
+ ],
85
+ "in_channels": 3,
86
+ "latent_channels": 32,
87
+ "scaling_factor": 0.41407,
88
+ "upsample_block_type": "interpolate"
89
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd991d1b54ffabf22745c5885589d8f2a7bc59930d95d92bd741c4fc64454bb
3
+ size 1249044836