Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
omnimodel
config.json CHANGED
@@ -216,6 +216,8 @@
216
  "sensor_to_sensor_bounds": null
217
  }
218
  },
 
 
219
  "maskless_cross_view_band_keys": "other_views",
220
  "maskless_cross_view_band_radius": 0,
221
  "maskless_cross_view_include_frame_zero": false,
 
216
  "sensor_to_sensor_bounds": null
217
  }
218
  },
219
+ "maskless_cross_view_action_attends_action": false,
220
+ "maskless_cross_view_attends_action": false,
221
  "maskless_cross_view_band_keys": "other_views",
222
  "maskless_cross_view_band_radius": 0,
223
  "maskless_cross_view_include_frame_zero": false,
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
model_index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "Cosmos3MultiviewPipeline",
3
- "_diffusers_version": "0.39.0",
4
- "default_use_system_prompt": true,
5
  "enable_safety_checker": false,
6
  "safety_checker": [
7
  null,
@@ -17,13 +17,13 @@
17
  ],
18
  "text_tokenizer": [
19
  "transformers",
20
- "Qwen2TokenizerFast"
21
  ],
22
  "transformer": [
23
  "diffusers",
24
  "Cosmos3OmniTransformer"
25
  ],
26
- "use_native_flow_schedule": false,
27
  "vae": [
28
  "diffusers",
29
  "AutoencoderKLWan"
 
1
  {
2
  "_class_name": "Cosmos3MultiviewPipeline",
3
+ "_diffusers_version": "0.40.0",
4
+ "default_use_system_prompt": false,
5
  "enable_safety_checker": false,
6
  "safety_checker": [
7
  null,
 
17
  ],
18
  "text_tokenizer": [
19
  "transformers",
20
+ "Qwen2Tokenizer"
21
  ],
22
  "transformer": [
23
  "diffusers",
24
  "Cosmos3OmniTransformer"
25
  ],
26
+ "use_native_flow_schedule": true,
27
  "vae": [
28
  "diffusers",
29
  "AutoencoderKLWan"
modular_model_index.json CHANGED
@@ -1,13 +1,15 @@
1
  {
2
  "_blocks_class_name": "Cosmos3OmniBlocks",
3
  "_class_name": "Cosmos3OmniModularPipeline",
4
- "_diffusers_version": "0.39.0",
5
  "is_distilled": false,
 
 
6
  "scheduler": [
7
  "diffusers",
8
  "UniPCMultistepScheduler",
9
  {
10
- "pretrained_model_name_or_path": "diffusers_format2",
11
  "subfolder": "scheduler",
12
  "type_hint": [
13
  "diffusers",
@@ -18,13 +20,13 @@
18
  ],
19
  "text_tokenizer": [
20
  "transformers",
21
- "Qwen2TokenizerFast",
22
  {
23
- "pretrained_model_name_or_path": "diffusers_format2",
24
  "subfolder": "text_tokenizer",
25
  "type_hint": [
26
  "transformers",
27
- "Qwen2TokenizerFast"
28
  ],
29
  "variant": null
30
  }
@@ -33,7 +35,7 @@
33
  "diffusers",
34
  "Cosmos3OmniTransformer",
35
  {
36
- "pretrained_model_name_or_path": "diffusers_format2",
37
  "subfolder": "transformer",
38
  "type_hint": [
39
  "diffusers",
@@ -42,11 +44,12 @@
42
  "variant": null
43
  }
44
  ],
 
45
  "vae": [
46
  "diffusers",
47
  "AutoencoderKLWan",
48
  {
49
- "pretrained_model_name_or_path": "diffusers_format2",
50
  "subfolder": "vae",
51
  "type_hint": [
52
  "diffusers",
 
1
  {
2
  "_blocks_class_name": "Cosmos3OmniBlocks",
3
  "_class_name": "Cosmos3OmniModularPipeline",
4
+ "_diffusers_version": "0.40.0",
5
  "is_distilled": false,
6
+ "default_use_system_prompt": false,
7
+ "enable_safety_checker": false,
8
  "scheduler": [
9
  "diffusers",
10
  "UniPCMultistepScheduler",
11
  {
12
+ "pretrained_model_name_or_path": "diffusers_format7",
13
  "subfolder": "scheduler",
14
  "type_hint": [
15
  "diffusers",
 
20
  ],
21
  "text_tokenizer": [
22
  "transformers",
23
+ "Qwen2Tokenizer",
24
  {
25
+ "pretrained_model_name_or_path": "diffusers_format7",
26
  "subfolder": "text_tokenizer",
27
  "type_hint": [
28
  "transformers",
29
+ "Qwen2Tokenizer"
30
  ],
31
  "variant": null
32
  }
 
35
  "diffusers",
36
  "Cosmos3OmniTransformer",
37
  {
38
+ "pretrained_model_name_or_path": "diffusers_format7",
39
  "subfolder": "transformer",
40
  "type_hint": [
41
  "diffusers",
 
44
  "variant": null
45
  }
46
  ],
47
+ "use_native_flow_schedule": true,
48
  "vae": [
49
  "diffusers",
50
  "AutoencoderKLWan",
51
  {
52
+ "pretrained_model_name_or_path": "diffusers_format7",
53
  "subfolder": "vae",
54
  "type_hint": [
55
  "diffusers",
scheduler/scheduler_config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "_class_name": "UniPCMultistepScheduler",
3
- "_diffusers_version": "0.39.0",
4
  "beta_end": 0.02,
5
  "beta_schedule": "linear",
6
  "beta_start": 0.0001,
7
  "disable_corrector": [],
8
  "dynamic_thresholding_ratio": 0.995,
9
  "final_sigmas_type": "zero",
10
- "flow_shift": 1.0,
11
  "lower_order_final": true,
12
  "num_train_timesteps": 1000,
13
  "predict_x0": true,
@@ -15,8 +15,8 @@
15
  "rescale_betas_zero_snr": false,
16
  "sample_max_value": 1.0,
17
  "shift_terminal": null,
18
- "sigma_max": 200.0,
19
- "sigma_min": 0.147,
20
  "solver_order": 2,
21
  "solver_p": null,
22
  "solver_type": "bh2",
@@ -29,5 +29,5 @@
29
  "use_dynamic_shifting": false,
30
  "use_exponential_sigmas": false,
31
  "use_flow_sigmas": true,
32
- "use_karras_sigmas": true
33
  }
 
1
  {
2
  "_class_name": "UniPCMultistepScheduler",
3
+ "_diffusers_version": "0.40.0",
4
  "beta_end": 0.02,
5
  "beta_schedule": "linear",
6
  "beta_start": 0.0001,
7
  "disable_corrector": [],
8
  "dynamic_thresholding_ratio": 0.995,
9
  "final_sigmas_type": "zero",
10
+ "flow_shift": 10.0,
11
  "lower_order_final": true,
12
  "num_train_timesteps": 1000,
13
  "predict_x0": true,
 
15
  "rescale_betas_zero_snr": false,
16
  "sample_max_value": 1.0,
17
  "shift_terminal": null,
18
+ "sigma_max": null,
19
+ "sigma_min": null,
20
  "solver_order": 2,
21
  "solver_p": null,
22
  "solver_type": "bh2",
 
29
  "use_dynamic_shifting": false,
30
  "use_exponential_sigmas": false,
31
  "use_flow_sigmas": true,
32
+ "use_karras_sigmas": false
33
  }
text_tokenizer/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
text_tokenizer/tokenizer_config.json CHANGED
@@ -1,217 +1,11 @@
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|>",
@@ -226,11 +20,8 @@
226
  "<|image_pad|>",
227
  "<|video_pad|>"
228
  ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
  "model_max_length": 262144,
235
  "pad_token": "<|endoftext|>",
236
  "split_special_tokens": false,
 
1
  {
 
2
  "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "<|im_start|>",
10
  "<|im_end|>",
11
  "<|object_ref_start|>",
 
20
  "<|image_pad|>",
21
  "<|video_pad|>"
22
  ],
23
+ "is_local": false,
24
+ "local_files_only": false,
 
 
 
25
  "model_max_length": 262144,
26
  "pad_token": "<|endoftext|>",
27
  "split_special_tokens": false,
transformer/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "Cosmos3OmniTransformer",
3
- "_diffusers_version": "0.39.0",
4
  "action_dim": 32,
5
  "action_gen": false,
6
  "attention_bias": false,
@@ -170,6 +170,7 @@
170
  20,
171
  20
172
  ],
 
173
  "rope_type": "default"
174
  },
175
  "rope_theta": 5000000,
 
1
  {
2
  "_class_name": "Cosmos3OmniTransformer",
3
+ "_diffusers_version": "0.40.0",
4
  "action_dim": 32,
5
  "action_gen": false,
6
  "attention_bias": false,
 
170
  20,
171
  20
172
  ],
173
+ "rope_theta": 5000000,
174
  "rope_type": "default"
175
  },
176
  "rope_theta": 5000000,
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKLWan",
3
- "_diffusers_version": "0.39.0",
4
  "_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
5
  "attn_scales": [],
6
  "base_dim": 160,
 
1
  {
2
  "_class_name": "AutoencoderKLWan",
3
+ "_diffusers_version": "0.40.0",
4
  "_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
5
  "attn_scales": [],
6
  "base_dim": 160,