Hugging Face's logo

FastVideo
/
FastVideo-FastH3-8-Step-V2-NVFP4-Consumer

Text-to-Video
Diffusers
Safetensors
MiniMaxH3ModularPipeline
video-generation
audio
fastvideo
nvfp4
Model card Files
xet
 Community
aryan5v commited on
Commit
540cfae
·
verified ·
1 Parent(s): 8bf0d7f

Add files using upload-large-folder tool

Browse files
Files changed (25) hide show
  1. README.md +19 -0
  2. audio_scheduler/scheduler_config.json +5 -0
  3. audio_vae/config.json +125 -0
  4. audio_vae/diffusion_pytorch_model.safetensors +3 -0
  5. fastvideo_inference.json +33 -0
  6. scheduler/scheduler_config.json +5 -0
  7. text_encoder/model-00002-of-00004.safetensors +3 -0
  8. text_encoder/model-00003-of-00004.safetensors +3 -0
  9. text_encoder/model-00004-of-00004.safetensors +3 -0
  10. tokenizer/merges.txt +0 -0
  11. tokenizer/tokenizer.json +0 -0
  12. tokenizer/tokenizer_config.json +246 -0
  13. tokenizer/vocab.json +0 -0
  14. transformer/config.json +26 -0
  15. transformer/diffusion_pytorch_model-00001-of-00006.safetensors +3 -0
  16. transformer/diffusion_pytorch_model-00002-of-00006.safetensors +3 -0
  17. transformer/diffusion_pytorch_model-00003-of-00006.safetensors +3 -0
  18. transformer/diffusion_pytorch_model-00004-of-00006.safetensors +3 -0
  19. transformer/diffusion_pytorch_model-00005-of-00006.safetensors +3 -0
  20. transformer/diffusion_pytorch_model-00006-of-00006.safetensors +3 -0
  21. transformer/diffusion_pytorch_model.safetensors.index.json +343 -0
  22. transformer/nvfp4_weights.safetensors +3 -0
  23. vae/config.json +97 -0
  24. vae/diffusion_pytorch_model.safetensors +3 -0
  25. vae/minimax_h3_video_vae_int8_convrot.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: FastVideo/FastVideo-FastH3-8-Step-V2
4
+ tags: [video-generation, text-to-video, audio, fastvideo, nvfp4]
5
+ ---
6
+ # FastH3 V2, 8-step, NVFP4 for one GPU
7
+
8
+ FastH3 V2 (8 distilled steps, video with synchronized audio) packaged for a single Blackwell GPU (RTX 5090,
9
+ RTX PRO 6000) or a DGX Spark.
10
+
11
+ - **Transformer:** FastH3 V2 (50 blocks). MLP linears keep the calibrated NVFP4 weights and activation scales from
12
+ [FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4);
13
+ attention projections and sparse-attention gates are also stored in NVFP4.
14
+ - **Text encoder:** NVFP4 Qwen3-VL trimmed to the 50 layers H3 reads.
15
+ - **VAE:** LynnReal lightweight video VAE with Kijai's INT8 weights; H3 audio VAE.
16
+ - **Sampling:** `fastvideo_inference.json` holds the 8-step DMD schedule, which FastVideo reads automatically.
17
+
18
+ For multi-GPU data-center serving, use [FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4).
19
+ Smaller, faster experimental variant: [FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4).
audio_scheduler/scheduler_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxH3Scheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "shift": 3.0
5
+ }
audio_vae/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLMiniMaxH3Audio",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "encoder_dim": 64,
5
+ "encoder_rates": [
6
+ 2,
7
+ 4,
8
+ 4,
9
+ 5,
10
+ 5
11
+ ],
12
+ "latent_dim": 2048,
13
+ "latent_channels": 32,
14
+ "decoder_dim": 1024,
15
+ "decoder_rates": [
16
+ 5,
17
+ 5,
18
+ 2,
19
+ 2,
20
+ 2,
21
+ 2,
22
+ 2
23
+ ],
24
+ "decoder_kernel_sizes": [
25
+ 9,
26
+ 9,
27
+ 4,
28
+ 4,
29
+ 4,
30
+ 4,
31
+ 4
32
+ ],
33
+ "num_attention_heads": 8,
34
+ "resblock_kernel_sizes": [
35
+ 3,
36
+ 7,
37
+ 11
38
+ ],
39
+ "resblock_dilation_sizes": [
40
+ [
41
+ 1,
42
+ 3,
43
+ 5
44
+ ],
45
+ [
46
+ 1,
47
+ 3,
48
+ 5
49
+ ],
50
+ [
51
+ 1,
52
+ 3,
53
+ 5
54
+ ]
55
+ ],
56
+ "sampling_rate": 32000,
57
+ "latents_mean": [
58
+ -0.020211687488382354,
59
+ 0.3876466479950502,
60
+ -0.04398279799186767,
61
+ -0.28591514936373,
62
+ 0.08179686214561671,
63
+ -0.35782641352446604,
64
+ 0.040623809960919084,
65
+ -0.01552534501956604,
66
+ -0.223362481667332,
67
+ 0.1821006842509091,
68
+ 0.2941778783780663,
69
+ -0.07901167601970885,
70
+ -0.056815072777201,
71
+ -0.3699028221860095,
72
+ -0.31616315591624855,
73
+ 0.5905951377425391,
74
+ -0.052139568068853864,
75
+ 0.013673160263486295,
76
+ -0.03691647864630577,
77
+ 0.09732660653298163,
78
+ -0.3394662328788498,
79
+ -0.30685677538541667,
80
+ -0.24504598907458763,
81
+ -0.034698524462007344,
82
+ 0.02868032184767538,
83
+ -0.21217779266454084,
84
+ -0.1678263169941987,
85
+ 0.3221287889040614,
86
+ -0.1223055851554907,
87
+ 0.4356604928128464,
88
+ -0.0502599202236253,
89
+ 0.3979258376211797
90
+ ],
91
+ "latents_std": [
92
+ 1.6895524230479284,
93
+ 2.76263727217653,
94
+ 1.7945344281264435,
95
+ 1.6801681847309828,
96
+ 1.6390226546605453,
97
+ 2.7788298348882177,
98
+ 1.7659090095747236,
99
+ 1.6199757612137327,
100
+ 2.6336525640336896,
101
+ 1.8539356672817833,
102
+ 2.5056497896915633,
103
+ 1.811019237886178,
104
+ 1.9579657790720237,
105
+ 1.6685498243529284,
106
+ 1.4922469314453364,
107
+ 3.298670198067373,
108
+ 1.9491804496832168,
109
+ 1.8720003270431442,
110
+ 1.8334080103291832,
111
+ 1.6488070416529093,
112
+ 1.6176957696319716,
113
+ 1.9131449234774398,
114
+ 1.5695245398428617,
115
+ 1.6943659940415912,
116
+ 1.8318420762504692,
117
+ 1.5540637421583379,
118
+ 1.9344930328968526,
119
+ 1.599198216109855,
120
+ 1.718045989838149,
121
+ 1.6307219190837705,
122
+ 1.8661226051202384,
123
+ 1.5613768203168363
124
+ ]
125
+ }
audio_vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c59e67ba8de5477c81bfbced0327aabf500f1bfdeefd5ee754529241cb26cb
3
+ size 605429340
fastvideo_inference.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_backend": "VIDEO_SPARSE_ATTN_H3",
3
+ "audio_scheduler_shift": 3.0,
4
+ "checkpoint_step": 1300,
5
+ "dmd_denoising_steps": [
6
+ 999,
7
+ 874,
8
+ 749,
9
+ 624,
10
+ 500,
11
+ 375,
12
+ 250,
13
+ 125
14
+ ],
15
+ "fastvideo_commit": "24bbe7fddd05ca6f2c34b3dbed06ac1c75b72086",
16
+ "guidance_scale": 1.0,
17
+ "model_id": "FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4-Consumer",
18
+ "num_gpus": 4,
19
+ "num_inference_steps": 9,
20
+ "schema_version": "fasth3-inference-contract-v1",
21
+ "sequence_parallel_size": 4,
22
+ "task": "t2av",
23
+ "torch_compile": false,
24
+ "training_parent_run_id": "20260829T210445Z-h3-v14-8step-datafree-vsa80-vshift10",
25
+ "transformer_forwards": 8,
26
+ "use_fsdp_inference": true,
27
+ "video_scheduler_shift": 10.0,
28
+ "vsa_kernel": "sm100a",
29
+ "vsa_sparsity": 0.8,
30
+ "vsa_tile_size": 64,
31
+ "quantization": "nvfp4_attention_mlp_gate",
32
+ "source_model": "FastVideo/FastVideo-FastH3-8-Step-V2"
33
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxH3Scheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "shift": 10.0
5
+ }
text_encoder/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff092cd64c489ce4609a08ba5d9f8548591bf835cd98fa4154a7eccd0ea16dfd
3
+ size 4270035088
text_encoder/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dab4af0342cfc9b31839458d059327c7cd1e5be1fe779ded253939cabb36a51
3
+ size 4241221712
text_encoder/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628852eb94bd2e3c297d120683f900b49051f236e2cd9d1f26476c30cedc2add
3
+ size 3659204564
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<d>",
229
+ "</d>",
230
+ "<|cutoff|>",
231
+ "<|lyrics_start|>",
232
+ "<|lyrics_end|>",
233
+ "<|caption_start|>",
234
+ "<|caption_end|>"
235
+ ],
236
+ "bos_token": null,
237
+ "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",
238
+ "clean_up_tokenization_spaces": false,
239
+ "eos_token": "<|im_end|>",
240
+ "errors": "replace",
241
+ "model_max_length": 262144,
242
+ "pad_token": "<|endoftext|>",
243
+ "split_special_tokens": false,
244
+ "tokenizer_class": "Qwen2Tokenizer",
245
+ "unk_token": null
246
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxH3Transformer3DModel",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "num_attention_heads": 56,
5
+ "attention_head_dim": 128,
6
+ "hidden_size": 5376,
7
+ "num_layers": 50,
8
+ "num_refiner_layers": 2,
9
+ "ffn_dim": 14336,
10
+ "in_channels": 24,
11
+ "audio_in_channels": 32,
12
+ "patch_size": [
13
+ 1,
14
+ 2,
15
+ 2
16
+ ],
17
+ "text_dim": 5120,
18
+ "freq_dim": 256,
19
+ "time_embed_hidden_dim": 5376,
20
+ "time_embed_dim": 2688,
21
+ "rope_freq_dim": 16,
22
+ "rope_theta": 10000.0,
23
+ "norm_eps": 1e-05,
24
+ "qk_norm_eps": 1e-05,
25
+ "final_norm_eps": 1e-05
26
+ }
transformer/diffusion_pytorch_model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1650a7ffce97cc5d0b3b99e226ac237701e753a61d971e6b7870b686876f83a
3
+ size 5331870504
transformer/diffusion_pytorch_model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67f2734003051e1723fc55a57d769810f347b0d17af8c7f9c618ef6db6b0056
3
+ size 5204410000
transformer/diffusion_pytorch_model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cffd8d067f0f85ee378fba7f88b5d6416ceffaa75139f7d4d467abb55c7c3ea7
3
+ size 5204410000
transformer/diffusion_pytorch_model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db41a003f6d23abf7c64e5709e99e8dc897436da9557f9d33dc4fb1cff03dba0
3
+ size 5204410000
transformer/diffusion_pytorch_model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e69e359939bbf2c4fe269d7a0d652ee6fd3c6511a6ace83e079da4479307289
3
+ size 5204410000
transformer/diffusion_pytorch_model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2bcf98a5b91da3914853b6524b1138201f98868ee8e38951038b8e30bbac9b
3
+ size 1561345392
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {},
3
+ "weight_map": {
4
+ "audio_proj_in.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
5
+ "audio_proj_in.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
6
+ "audio_proj_out.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
7
+ "audio_proj_out.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
8
+ "context_embedder.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
9
+ "context_embedder.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
10
+ "norm_out.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
11
+ "norm_out.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
12
+ "norm_out.norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
13
+ "proj_in.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
14
+ "proj_in.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
15
+ "proj_out.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
16
+ "proj_out.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
17
+ "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
18
+ "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
19
+ "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
20
+ "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
21
+ "token_refiner.final_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
22
+ "token_refiner.refiner_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
23
+ "token_refiner.refiner_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
24
+ "token_refiner.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
25
+ "token_refiner.refiner_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
26
+ "token_refiner.refiner_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
27
+ "token_refiner.refiner_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
28
+ "token_refiner.refiner_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
29
+ "token_refiner.refiner_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
30
+ "token_refiner.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
31
+ "token_refiner.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
32
+ "token_refiner.refiner_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
33
+ "token_refiner.refiner_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
34
+ "token_refiner.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
35
+ "token_refiner.refiner_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
36
+ "token_refiner.refiner_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
37
+ "token_refiner.refiner_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
38
+ "token_refiner.refiner_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
39
+ "token_refiner.refiner_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
40
+ "token_refiner.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
41
+ "token_refiner.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
42
+ "transformer_blocks.0.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
43
+ "transformer_blocks.0.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
44
+ "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
45
+ "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
46
+ "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
47
+ "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
48
+ "transformer_blocks.1.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
49
+ "transformer_blocks.1.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
50
+ "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
51
+ "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
52
+ "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
53
+ "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
54
+ "transformer_blocks.10.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
55
+ "transformer_blocks.10.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
56
+ "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
57
+ "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
58
+ "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
59
+ "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
60
+ "transformer_blocks.11.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
61
+ "transformer_blocks.11.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
62
+ "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
63
+ "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
64
+ "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
65
+ "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
66
+ "transformer_blocks.12.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
67
+ "transformer_blocks.12.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
68
+ "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
69
+ "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
70
+ "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
71
+ "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
72
+ "transformer_blocks.13.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
73
+ "transformer_blocks.13.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
74
+ "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
75
+ "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
76
+ "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
77
+ "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
78
+ "transformer_blocks.14.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
79
+ "transformer_blocks.14.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
80
+ "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
81
+ "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
82
+ "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
83
+ "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
84
+ "transformer_blocks.15.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
85
+ "transformer_blocks.15.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
86
+ "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
87
+ "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
88
+ "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
89
+ "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
90
+ "transformer_blocks.16.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
91
+ "transformer_blocks.16.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
92
+ "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
93
+ "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
94
+ "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
95
+ "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
96
+ "transformer_blocks.17.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
97
+ "transformer_blocks.17.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
98
+ "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
99
+ "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
100
+ "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
101
+ "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
102
+ "transformer_blocks.18.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
103
+ "transformer_blocks.18.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
104
+ "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
105
+ "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
106
+ "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
107
+ "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
108
+ "transformer_blocks.19.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
109
+ "transformer_blocks.19.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
110
+ "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
111
+ "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
112
+ "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
113
+ "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
114
+ "transformer_blocks.2.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
115
+ "transformer_blocks.2.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
116
+ "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
117
+ "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
118
+ "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
119
+ "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
120
+ "transformer_blocks.20.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
121
+ "transformer_blocks.20.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
122
+ "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
123
+ "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
124
+ "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
125
+ "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
126
+ "transformer_blocks.21.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
127
+ "transformer_blocks.21.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
128
+ "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
129
+ "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
130
+ "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
131
+ "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
132
+ "transformer_blocks.22.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
133
+ "transformer_blocks.22.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
134
+ "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
135
+ "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
136
+ "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
137
+ "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
138
+ "transformer_blocks.23.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
139
+ "transformer_blocks.23.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
140
+ "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
141
+ "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
142
+ "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
143
+ "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
144
+ "transformer_blocks.24.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
145
+ "transformer_blocks.24.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
146
+ "transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
147
+ "transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
148
+ "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
149
+ "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
150
+ "transformer_blocks.25.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
151
+ "transformer_blocks.25.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
152
+ "transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
153
+ "transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
154
+ "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
155
+ "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
156
+ "transformer_blocks.26.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
157
+ "transformer_blocks.26.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
158
+ "transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
159
+ "transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
160
+ "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
161
+ "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
162
+ "transformer_blocks.27.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
163
+ "transformer_blocks.27.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
164
+ "transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
165
+ "transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
166
+ "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
167
+ "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
168
+ "transformer_blocks.28.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
169
+ "transformer_blocks.28.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
170
+ "transformer_blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
171
+ "transformer_blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
172
+ "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
173
+ "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
174
+ "transformer_blocks.29.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
175
+ "transformer_blocks.29.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
176
+ "transformer_blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
177
+ "transformer_blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
178
+ "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
179
+ "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
180
+ "transformer_blocks.3.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
181
+ "transformer_blocks.3.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
182
+ "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
183
+ "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
184
+ "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
185
+ "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
186
+ "transformer_blocks.30.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
187
+ "transformer_blocks.30.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
188
+ "transformer_blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
189
+ "transformer_blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
190
+ "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
191
+ "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
192
+ "transformer_blocks.31.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
193
+ "transformer_blocks.31.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
194
+ "transformer_blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
195
+ "transformer_blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
196
+ "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
197
+ "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
198
+ "transformer_blocks.32.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
199
+ "transformer_blocks.32.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
200
+ "transformer_blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
201
+ "transformer_blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
202
+ "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
203
+ "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
204
+ "transformer_blocks.33.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
205
+ "transformer_blocks.33.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
206
+ "transformer_blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
207
+ "transformer_blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
208
+ "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
209
+ "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
210
+ "transformer_blocks.34.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
211
+ "transformer_blocks.34.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
212
+ "transformer_blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
213
+ "transformer_blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
214
+ "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
215
+ "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
216
+ "transformer_blocks.35.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
217
+ "transformer_blocks.35.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
218
+ "transformer_blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
219
+ "transformer_blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
220
+ "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
221
+ "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
222
+ "transformer_blocks.36.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
223
+ "transformer_blocks.36.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
224
+ "transformer_blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
225
+ "transformer_blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
226
+ "transformer_blocks.36.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
227
+ "transformer_blocks.36.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
228
+ "transformer_blocks.37.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
229
+ "transformer_blocks.37.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
230
+ "transformer_blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
231
+ "transformer_blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
232
+ "transformer_blocks.37.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
233
+ "transformer_blocks.37.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
234
+ "transformer_blocks.38.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
235
+ "transformer_blocks.38.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
236
+ "transformer_blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
237
+ "transformer_blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
238
+ "transformer_blocks.38.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
239
+ "transformer_blocks.38.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
240
+ "transformer_blocks.39.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
241
+ "transformer_blocks.39.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
242
+ "transformer_blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
243
+ "transformer_blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
244
+ "transformer_blocks.39.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
245
+ "transformer_blocks.39.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
246
+ "transformer_blocks.4.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
247
+ "transformer_blocks.4.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
248
+ "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
249
+ "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
250
+ "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
251
+ "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
252
+ "transformer_blocks.40.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
253
+ "transformer_blocks.40.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
254
+ "transformer_blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
255
+ "transformer_blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
256
+ "transformer_blocks.40.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
257
+ "transformer_blocks.40.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
258
+ "transformer_blocks.41.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
259
+ "transformer_blocks.41.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
260
+ "transformer_blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
261
+ "transformer_blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
262
+ "transformer_blocks.41.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
263
+ "transformer_blocks.41.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
264
+ "transformer_blocks.42.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
265
+ "transformer_blocks.42.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
266
+ "transformer_blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
267
+ "transformer_blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
268
+ "transformer_blocks.42.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
269
+ "transformer_blocks.42.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
270
+ "transformer_blocks.43.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
271
+ "transformer_blocks.43.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
272
+ "transformer_blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
273
+ "transformer_blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
274
+ "transformer_blocks.43.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
275
+ "transformer_blocks.43.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
276
+ "transformer_blocks.44.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
277
+ "transformer_blocks.44.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
278
+ "transformer_blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
279
+ "transformer_blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
280
+ "transformer_blocks.44.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
281
+ "transformer_blocks.44.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
282
+ "transformer_blocks.45.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
283
+ "transformer_blocks.45.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
284
+ "transformer_blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
285
+ "transformer_blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
286
+ "transformer_blocks.45.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
287
+ "transformer_blocks.45.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
288
+ "transformer_blocks.46.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
289
+ "transformer_blocks.46.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
290
+ "transformer_blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
291
+ "transformer_blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
292
+ "transformer_blocks.46.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
293
+ "transformer_blocks.46.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
294
+ "transformer_blocks.47.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
295
+ "transformer_blocks.47.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
296
+ "transformer_blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
297
+ "transformer_blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
298
+ "transformer_blocks.47.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
299
+ "transformer_blocks.47.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
300
+ "transformer_blocks.48.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
301
+ "transformer_blocks.48.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
302
+ "transformer_blocks.48.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
303
+ "transformer_blocks.48.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
304
+ "transformer_blocks.48.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
305
+ "transformer_blocks.48.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
306
+ "transformer_blocks.49.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
307
+ "transformer_blocks.49.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
308
+ "transformer_blocks.49.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
309
+ "transformer_blocks.49.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
310
+ "transformer_blocks.49.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
311
+ "transformer_blocks.49.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
312
+ "transformer_blocks.5.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
313
+ "transformer_blocks.5.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
314
+ "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
315
+ "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
316
+ "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
317
+ "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
318
+ "transformer_blocks.6.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
319
+ "transformer_blocks.6.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
320
+ "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
321
+ "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
322
+ "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
323
+ "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
324
+ "transformer_blocks.7.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
325
+ "transformer_blocks.7.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
326
+ "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
327
+ "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
328
+ "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
329
+ "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
330
+ "transformer_blocks.8.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
331
+ "transformer_blocks.8.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
332
+ "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
333
+ "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
334
+ "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
335
+ "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
336
+ "transformer_blocks.9.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
337
+ "transformer_blocks.9.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
338
+ "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
339
+ "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
340
+ "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
341
+ "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors"
342
+ }
343
+ }
transformer/nvfp4_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d620a57e2e3559712b396a279dc3c2aaf4dd70d54a870c25e4c2df60b874a7d
3
+ size 11921994548
vae/config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLMiniMaxH3",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "in_channels": 3,
5
+ "out_channels": 3,
6
+ "latent_channels": 24,
7
+ "block_out_channels": [
8
+ 128,
9
+ 256,
10
+ 256,
11
+ 512,
12
+ 512,
13
+ 1024
14
+ ],
15
+ "layers_per_block": 2,
16
+ "spatial_downsample_factors": [
17
+ 2,
18
+ 2,
19
+ 2,
20
+ 2,
21
+ 1,
22
+ 1
23
+ ],
24
+ "temporal_downsample_factors": [
25
+ 1,
26
+ 2,
27
+ 2,
28
+ 1,
29
+ 1,
30
+ 1
31
+ ],
32
+ "norm_num_groups": 32,
33
+ "norm_eps": 1e-06,
34
+ "spatial_padding_mode": "reflect",
35
+ "decoder_num_layers": 26,
36
+ "decoder_num_attention_heads": 32,
37
+ "decoder_attention_head_dim": 64,
38
+ "decoder_num_register_tokens": 4,
39
+ "decoder_ffn_mult": 4,
40
+ "decoder_rope_theta": 100.0,
41
+ "decoder_rope_dim_ratio": 0.75,
42
+ "decoder_norm_eps": 1e-05,
43
+ "clip_length": 17,
44
+ "token_drop": 3,
45
+ "latents_mean": [
46
+ 0.858090341091156,
47
+ -0.9606591463088989,
48
+ 1.0661640167236328,
49
+ -0.5090325474739075,
50
+ -0.2727581858634949,
51
+ -1.3675414323806763,
52
+ -0.2553254961967468,
53
+ -0.26907554268836975,
54
+ -0.5376840829849243,
55
+ -0.0464097298681736,
56
+ 0.6657370328903198,
57
+ 0.19690127670764923,
58
+ -0.5460608005523682,
59
+ -0.4035342037677765,
60
+ -0.23683024942874908,
61
+ 0.25928452610969543,
62
+ -0.30133944749832153,
63
+ 0.211341992020607,
64
+ -1.1206848621368408,
65
+ 0.3581933379173279,
66
+ -0.04225143790245056,
67
+ 0.2604829967021942,
68
+ 0.22864092886447906,
69
+ 0.7056031823158264
70
+ ],
71
+ "latents_std": [
72
+ 1.2223774194717407,
73
+ 1.2767263650894165,
74
+ 1.6831774711608887,
75
+ 1.7549455165863037,
76
+ 1.5636216402053833,
77
+ 2.194143533706665,
78
+ 0.9653137922286987,
79
+ 1.0569885969161987,
80
+ 0.841948926448822,
81
+ 0.7729952931404114,
82
+ 1.8955937623977661,
83
+ 0.946841835975647,
84
+ 0.7996809482574463,
85
+ 0.44988900423049927,
86
+ 0.7197399735450745,
87
+ 0.6936293244361877,
88
+ 2.961095094680786,
89
+ 2.7694199085235596,
90
+ 3.0496184825897217,
91
+ 2.1088054180145264,
92
+ 3.276226282119751,
93
+ 3.1627357006073,
94
+ 2.2816812992095947,
95
+ 2.6127843856811523
96
+ ]
97
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73fc5a61caeba438633eb8f8efd3a57f4915adfa46731a1c991312c724a3b5cc
3
+ size 4225603880
vae/minimax_h3_video_vae_int8_convrot.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11f8b9b96c9dd22b36bc6c18464b6929c207d247e6d865d90fe31588e58e7e2
3
+ size 2137493384