audio-cpp commited on
Commit
5b372e2
·
verified ·
1 Parent(s): 5e39f56

Add LiveAvatar GGUF models and examples

Browse files
.gitattributes CHANGED
@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Wan2.2-S2V-14B-NVFP4-LORA.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Wan2.2-S2V-Support-Q4_K_S-F16.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Wan2.2-S2V-VAE-F16.gguf filter=lfs diff=lfs merge=lfs -text
39
+ examples/cyclops/output-480p-cache2.mp4 filter=lfs diff=lfs merge=lfs -text
40
+ examples/cyclops/output-480p-cache3.mp4 filter=lfs diff=lfs merge=lfs -text
41
+ examples/cyclops/output-720p-weight-streaming.mp4 filter=lfs diff=lfs merge=lfs -text
42
+ examples/cyclops/reference.wav filter=lfs diff=lfs merge=lfs -text
43
+ examples/dwarven_blacksmith.wav filter=lfs diff=lfs merge=lfs -text
44
+ examples/quality/flash-attention.mp4 filter=lfs diff=lfs merge=lfs -text
45
+ examples/quality/layerwise-16.mp4 filter=lfs diff=lfs merge=lfs -text
46
+ examples/quality/reference.mp4 filter=lfs diff=lfs merge=lfs -text
47
+ examples/quality/target-cache-1.mp4 filter=lfs diff=lfs merge=lfs -text
48
+ examples/quality/target-cache-4.mp4 filter=lfs diff=lfs merge=lfs -text
49
+ examples/quality/vae-cache-f16.mp4 filter=lfs diff=lfs merge=lfs -text
50
+ examples/quality/vae-tile-320.mp4 filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright [yyyy] [name of copyright owner]
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
README.md ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Wan-AI/Wan2.2-S2V-14B
4
+ library_name: audio.cpp
5
+ pipeline_tag: image-to-video
6
+ tags:
7
+ - audio.cpp
8
+ - gguf
9
+ - audio-to-video
10
+ - liveavatar
11
+ - wan2.2
12
+ ---
13
+
14
+ # LiveAvatar GGUF for audio.cpp
15
+
16
+ Native GGUF package of [Wan-AI/Wan2.2-S2V-14B](https://huggingface.co/Wan-AI/Wan2.2-S2V-14B)
17
+ with the official [Quark-Vision/Live-Avatar](https://huggingface.co/Quark-Vision/Live-Avatar)
18
+ LoRA merged for [audio.cpp](https://github.com/0xShug0/audio.cpp). LiveAvatar
19
+ generates an audio-driven avatar video from a reference image, speech audio,
20
+ and a text description.
21
+
22
+ ## Files
23
+
24
+ | File | Description |
25
+ |---|---|
26
+ | `Wan2.2-S2V-Support-Q4_K_S-F16.gguf` | UMT5 text encoder, Wav2Vec2 audio encoder, tokenizer, and embedded audio.cpp model specification. |
27
+ | `Wan2.2-S2V-VAE-F16.gguf` | Wan video VAE in F16 with the embedded audio.cpp model specification. |
28
+ | `Wan2.2-S2V-14B-NVFP4-LORA.gguf` | LiveAvatar Wan2.2 S2V denoiser with the official LiveAvatar adapter. |
29
+
30
+ All three files are required.
31
+
32
+ ## Low-VRAM mode
33
+
34
+ LiveAvatar can keep the denoiser transformer blocks in pinned host memory and
35
+ stage one layer group at a time. This makes 720p generation possible near a
36
+ 16 GiB VRAM limit, at the cost of additional host-to-device transfers.
37
+
38
+ The validated 1280x720 run generated 93 frames at 16 FPS (5.81 seconds of
39
+ video) in **276 seconds wall time** (4 minutes 36 seconds) and peaked at
40
+ **15,993 MiB VRAM** on an RTX 5090.
41
+
42
+ | Control | Value |
43
+ |---|---:|
44
+ | `liveavatar.denoiser_weight_streaming` | `true` |
45
+ | `denoiser_layerwise` | `true` |
46
+ | `denoiser_layerwise_batch` | `16` |
47
+ | `target_cache_blocks` | `1` |
48
+ | `vae_cache_f16` | `true` |
49
+ | `vae_encoder_chunk_size` | `4` |
50
+ | `vae_decoder_tile_size` | `320` |
51
+
52
+ Weight streaming is slower than the normal resident-weight path. In a matched
53
+ 240p comparison, model time increased from 13.33 to 21.73 seconds, or about
54
+ **1.63x slower**. The exact slowdown depends on resolution, hardware, and host
55
+ memory bandwidth.
56
+
57
+ ### Full-duration 720p example
58
+
59
+ This example uses the official LiveAvatar
60
+ [Cyclops Baker image](examples/cyclops/reference.jpg) and
61
+ [speech audio](examples/cyclops/reference.wav). The official reference image is
62
+ only **720x400**, so this example also shows 1280x720 generation from a
63
+ lower-resolution image condition. The complete 11.6-second WAV is retained in
64
+ the generated video.
65
+
66
+ ![Official Cyclops Baker reference](examples/cyclops/reference.jpg)
67
+
68
+ <video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/cyclops/output-720p-weight-streaming.mp4"></video>
69
+
70
+ [Download the generated video](examples/cyclops/output-720p-weight-streaming.mp4)
71
+
72
+ | Measurement | Result |
73
+ |---|---:|
74
+ | Reference image | 720x400 |
75
+ | Reference audio | 11.60 s, 24 kHz mono |
76
+ | Output | 1280x720, 16 FPS, 11.60 s |
77
+ | Generated frames | 189 before audio-length muxing |
78
+ | LiveAvatar clips | 4 |
79
+ | Peak VRAM | 16,126 MiB (15.75 GiB) |
80
+ | Session time | 543.03 s (9 min 3 s) |
81
+ | Full CLI wall time | 557.33 s (9 min 17 s) |
82
+
83
+ The run used the low-VRAM controls above with denoiser weight streaming,
84
+ layerwise batch size 16, one target-cache block, F16 VAE cache, VAE encoder
85
+ chunk size 4, and VAE decoder tile size 320. Measurements were collected with
86
+ the CUDA debug build on an NVIDIA GeForce RTX 5090.
87
+
88
+ ### 480p cache trade-off
89
+
90
+ These two videos use the same Cyclops Baker inputs, prompt, seed, four clips,
91
+ and complete 11.6-second audio. Only `target_cache_blocks` changes. A longer
92
+ cache retains more temporal context from preceding video blocks and can improve
93
+ continuity across clip boundaries, but it does not directly increase per-frame
94
+ resolution or detail.
95
+
96
+ | Target cache | Peak VRAM | Peak host RAM | Session time | Practical trade-off |
97
+ |---:|---:|---:|---:|---|
98
+ | 2 blocks | 15,311 MiB | 43.33 GiB | 317.92 s | Lower memory and faster; recommended for iteration. |
99
+ | 3 blocks | 19,357 MiB | 56.94 GiB | 512.69 s | More temporal history, but nearly exhausts a 64 GB host and uses swap. |
100
+
101
+ <table>
102
+ <tr>
103
+ <td width="50%"><strong>Two cache blocks</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/cyclops/output-480p-cache2.mp4"></video><br><code>target_cache_blocks=2</code></td>
104
+ <td width="50%"><strong>Three cache blocks</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/cyclops/output-480p-cache3.mp4"></video><br><code>target_cache_blocks=3</code></td>
105
+ </tr>
106
+ </table>
107
+
108
+ 480p is the better starting point for prompt, identity, motion, and cache-window
109
+ experiments. Iterate at 480p, select the strongest result, and upscale that
110
+ video afterward instead of paying the 720p generation cost for every attempt.
111
+
112
+ ## Quality comparison
113
+
114
+ Each clip uses the same reference image, audio, prompt, seed `420`, four Euler
115
+ steps, guidance `0`, scheduler shift `3`, `416x240` resolution, 16 FPS, and 84
116
+ requested frames (81 output frames, 5.06 seconds). The reference uses
117
+ SageAttention, `memory_saver=true`, full target cache, F32 VAE cache, no VAE
118
+ tiling, and non-layerwise denoising. Each other cell changes only the parameter
119
+ shown below the video.
120
+
121
+ Inputs: [reference speech](examples/dwarven_blacksmith.wav) and
122
+ [reference image](examples/dwarven_blacksmith.jpg).
123
+
124
+ Prompt: `A stout, cheerful dwarf with a magnificent braided beard adorned with
125
+ metal rings, wearing a heavy leather apron. He is standing in his fiery,
126
+ cluttered forge, laughing heartily as he explains the mastery of his craft,
127
+ holding up a glowing hammer. Style of Blizzard Entertainment cinematics, warm,
128
+ dynamic lighting from the forge.`
129
+
130
+ Measured with the CUDA debug build on an NVIDIA GeForce RTX 5090. Wall time
131
+ includes model loading and output generation. Peak VRAM is total device memory
132
+ used during the run.
133
+
134
+ | Case | Controlled option | Peak VRAM (MiB) | Wall time (s) |
135
+ |---|---|---:|---:|
136
+ | Reference | Reference controls | 25,586 | 24.44 |
137
+ | FlashAttention | `sage_attention=false` | 25,990 | 24.90 |
138
+ | F16 VAE cache | `vae_cache_f16=true` | 22,896 | 25.16 |
139
+ | VAE decoder tiling | `vae_decoder_tile_size=320` | 25,566 | 24.51 |
140
+ | Target cache: 1 block | `target_cache_blocks=1` | 19,935 | 23.28 |
141
+ | Target cache: 4 blocks | `target_cache_blocks=4` | 22,761 | 24.40 |
142
+ | Layerwise denoising | `denoiser_layerwise=true`, `denoiser_layerwise_batch=16` | 25,333 | 26.62 |
143
+
144
+ <table>
145
+ <tr>
146
+ <td width="50%"><strong>Reference</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/reference.mp4"></video><br><code>reference controls</code></td>
147
+ <td width="50%"><strong>FlashAttention</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/flash-attention.mp4"></video><br><code>sage_attention=false</code></td>
148
+ </tr>
149
+ <tr>
150
+ <td width="50%"><strong>F16 VAE cache (current default)</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/vae-cache-f16.mp4"></video><br><code>vae_cache_f16=true</code></td>
151
+ <td width="50%"><strong>VAE decoder tiling</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/vae-tile-320.mp4"></video><br><code>vae_decoder_tile_size=320</code></td>
152
+ </tr>
153
+ <tr>
154
+ <td width="50%"><strong>Target cache: 1 block</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/target-cache-1.mp4"></video><br><code>target_cache_blocks=1</code></td>
155
+ <td width="50%"><strong>Target cache: 4 blocks</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/target-cache-4.mp4"></video><br><code>target_cache_blocks=4</code></td>
156
+ </tr>
157
+ <tr>
158
+ <td width="50%"><strong>Layerwise denoising</strong><br><video controls playsinline preload="metadata" width="100%" src="https://huggingface.co/audio-cpp/LiveAvatar-GGUF/resolve/main/examples/quality/layerwise-16.mp4"></video><br><code>denoiser_layerwise=true</code>, <code>denoiser_layerwise_batch=16</code></td>
159
+ <td width="50%"></td>
160
+ </tr>
161
+ </table>
162
+
163
+ ## Run
164
+
165
+ ```bash
166
+ audiocpp_cli \
167
+ --task gen \
168
+ --family liveavatar \
169
+ --model /path/to/LiveAvatar-GGUF \
170
+ --backend cuda \
171
+ --threads 8 \
172
+ --audio /path/to/reference.wav \
173
+ --text "A detailed description of the speaker and scene." \
174
+ --request-option generation_mode=liveavatar \
175
+ --request-option reference_image_path=/path/to/reference.jpg \
176
+ --request-option height=240 \
177
+ --request-option width=416 \
178
+ --out-dir outputs/liveavatar \
179
+ --log
180
+ ```
181
+
182
+ The default LiveAvatar configuration uses four Euler steps, scheduler shift 3,
183
+ guidance scale 0, seed 420, 48 frames per clip, SageAttention, and 16 FPS.
184
+
185
+ For lower VRAM use, add:
186
+
187
+ ```bash
188
+ --session-option liveavatar.denoiser_weight_streaming=true \
189
+ --request-option denoiser_layerwise=true \
190
+ --request-option denoiser_layerwise_batch=16
191
+ ```
192
+
193
+ See the [audio.cpp LiveAvatar documentation](https://github.com/0xShug0/audio.cpp/blob/main/docs/community_models/liveavatar.md)
194
+ for resolution, duration, and memory-control options.
195
+
196
+ ## License
197
+
198
+ LiveAvatar and its Wan2.2 base model are released under the Apache License 2.0.
199
+ This repository includes the upstream license in `LICENSE`. The GGUF conversion
200
+ is a packaging format for audio.cpp and is not an official upstream release.
Wan2.2-S2V-14B-NVFP4-LORA.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2472a69905851e58dc26f13a94ed14b866b231133586b853ac43d8b8ee56df
3
+ size 13861762016
Wan2.2-S2V-Support-Q4_K_S-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736800d885bdbdd932c4791db7aff010efe6454e2a43d3e52cf825ea9061233c
3
+ size 4126833344
Wan2.2-S2V-VAE-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be08379979976835a7a3ac689bc4ffb2f2f66d3124ae9342c688fc0c8aae550
3
+ size 253824672
examples/cyclops/output-480p-cache2.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50079d389b71d77a5beee9090014d91fb4a10153ff896c6b9228315998648f39
3
+ size 869074
examples/cyclops/output-480p-cache3.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89509c58d16a74e3dc8e4598fecf6d6234991b0d989e9a2c5cac9c90a4502b5a
3
+ size 881273
examples/cyclops/output-720p-weight-streaming.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea81cf87480d7742d985143ffb62eb8cb1b6f18e916503e6566256307814dc1
3
+ size 1551342
examples/cyclops/reference.jpg ADDED
examples/cyclops/reference.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876b8691ba0ed158f2fd7c04a32c7dba70cda0a4e49311fdc9723a22965c2f92
3
+ size 1113680
examples/dwarven_blacksmith.jpg ADDED
examples/dwarven_blacksmith.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8badf0fcbd9066d456a6ef7b27e95bef169b9e6ba46c843423a6b61e49fc97c5
3
+ size 1701200
examples/quality/flash-attention.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c357f1ad2ee1886c690da39ebddd8b3956710fdc19a980610dd35feb415f73
3
+ size 219982
examples/quality/layerwise-16.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8650350b06873c40bf4f8c711c1656af38301234782d142aeb6351ffd72674
3
+ size 220133
examples/quality/reference.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8650350b06873c40bf4f8c711c1656af38301234782d142aeb6351ffd72674
3
+ size 220133
examples/quality/target-cache-1.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7582448062b26ced960f09e7bc993a2373e1d7bb13b330b0814f5a0b180cc389
3
+ size 228230
examples/quality/target-cache-4.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d5d5cf2e8b4faca02f4b5624f7136eda6700d550d162d73b48d54b18d1ab10
3
+ size 221256
examples/quality/vae-cache-f16.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8908757690562db40d0240153fc94968a9bd5707a42d197bc369a7527f42222
3
+ size 217293
examples/quality/vae-tile-320.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8650350b06873c40bf4f8c711c1656af38301234782d142aeb6351ffd72674
3
+ size 220133