Spaces:
Running
on
T4
Running
on
T4
File size: 8,677 Bytes
73ed896 f47eaa6 73ed896 f47eaa6 73ed896 f47eaa6 73ed896 f47eaa6 73ed896 f47eaa6 73ed896 f47eaa6 73ed896 c5cb92f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
import gc
import logging
from argparse import ArgumentParser
from datetime import datetime
from fractions import Fraction
from pathlib import Path
import gradio as gr
import torch
import torchaudio
from mmaudio.eval_utils import (ModelConfig, VideoInfo, all_model_cfg, generate, load_image,
load_video, make_video, setup_eval_logging)
from mmaudio.model.flow_matching import FlowMatching
from mmaudio.model.networks import MMAudio, get_my_mmaudio
from mmaudio.model.sequence_config import SequenceConfig
from mmaudio.model.utils.features_utils import FeaturesUtils
torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.allow_tf32 = True
log = logging.getLogger()
device = 'cpu'
if torch.cuda.is_available():
device = 'cuda'
elif torch.backends.mps.is_available():
device = 'mps'
else:
log.warning('CUDA/MPS are not available, running on CPU')
dtype = torch.bfloat16
model: ModelConfig = all_model_cfg['large_44k_v2']
model.download_if_needed()
output_dir = Path('./output/gradio')
setup_eval_logging()
def get_model() -> tuple[MMAudio, FeaturesUtils, SequenceConfig]:
seq_cfg = model.seq_cfg
net: MMAudio = get_my_mmaudio(model.model_name).to(device, dtype).eval()
net.load_weights(torch.load(model.model_path, map_location=device, weights_only=True))
log.info(f'Loaded weights from {model.model_path}')
feature_utils = FeaturesUtils(tod_vae_ckpt=model.vae_path,
synchformer_ckpt=model.synchformer_ckpt,
enable_conditions=True,
mode=model.mode,
bigvgan_vocoder_ckpt=model.bigvgan_16k_path,
need_vae_encoder=False)
feature_utils = feature_utils.to(device, dtype).eval()
return net, feature_utils, seq_cfg
net, feature_utils, seq_cfg = get_model()
@torch.inference_mode()
def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, seed: int, num_steps: int,
cfg_strength: float, duration: float):
rng = torch.Generator(device=device)
if seed >= 0:
rng.manual_seed(seed)
else:
rng.seed()
fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
video_info = load_video(video, duration)
clip_frames = video_info.clip_frames
sync_frames = video_info.sync_frames
duration = video_info.duration_sec
clip_frames = clip_frames.unsqueeze(0)
sync_frames = sync_frames.unsqueeze(0)
seq_cfg.duration = duration
net.update_seq_lengths(seq_cfg.latent_seq_len, seq_cfg.clip_seq_len, seq_cfg.sync_seq_len)
audios = generate(clip_frames,
sync_frames, [prompt],
negative_text=[negative_prompt],
feature_utils=feature_utils,
net=net,
fm=fm,
rng=rng,
cfg_strength=cfg_strength)
audio = audios.float().cpu()[0]
current_time_string = datetime.now().strftime('%Y%m%d_%H%M%S')
output_dir.mkdir(exist_ok=True, parents=True)
video_save_path = output_dir / f'{current_time_string}.mp4'
make_video(video_info, video_save_path, audio, sampling_rate=seq_cfg.sampling_rate)
gc.collect()
return video_save_path
@torch.inference_mode()
def image_to_audio(image: gr.Image, prompt: str, negative_prompt: str, seed: int, num_steps: int,
cfg_strength: float, duration: float):
rng = torch.Generator(device=device)
if seed >= 0:
rng.manual_seed(seed)
else:
rng.seed()
fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
image_info = load_image(image)
clip_frames = image_info.clip_frames
sync_frames = image_info.sync_frames
clip_frames = clip_frames.unsqueeze(0)
sync_frames = sync_frames.unsqueeze(0)
seq_cfg.duration = duration
net.update_seq_lengths(seq_cfg.latent_seq_len, seq_cfg.clip_seq_len, seq_cfg.sync_seq_len)
audios = generate(clip_frames,
sync_frames, [prompt],
negative_text=[negative_prompt],
feature_utils=feature_utils,
net=net,
fm=fm,
rng=rng,
cfg_strength=cfg_strength,
image_input=True)
audio = audios.float().cpu()[0]
current_time_string = datetime.now().strftime('%Y%m%d_%H%M%S')
output_dir.mkdir(exist_ok=True, parents=True)
video_save_path = output_dir / f'{current_time_string}.mp4'
video_info = VideoInfo.from_image_info(image_info, duration, fps=Fraction(1))
make_video(video_info, video_save_path, audio, sampling_rate=seq_cfg.sampling_rate)
gc.collect()
return video_save_path
@torch.inference_mode()
def text_to_audio(prompt: str, negative_prompt: str, seed: int, num_steps: int, cfg_strength: float,
duration: float):
rng = torch.Generator(device=device)
if seed >= 0:
rng.manual_seed(seed)
else:
rng.seed()
fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
clip_frames = sync_frames = None
seq_cfg.duration = duration
net.update_seq_lengths(seq_cfg.latent_seq_len, seq_cfg.clip_seq_len, seq_cfg.sync_seq_len)
audios = generate(clip_frames,
sync_frames, [prompt],
negative_text=[negative_prompt],
feature_utils=feature_utils,
net=net,
fm=fm,
rng=rng,
cfg_strength=cfg_strength)
audio = audios.float().cpu()[0]
current_time_string = datetime.now().strftime('%Y%m%d_%H%M%S')
output_dir.mkdir(exist_ok=True, parents=True)
audio_save_path = output_dir / f'{current_time_string}.flac'
torchaudio.save(audio_save_path, audio, seq_cfg.sampling_rate)
gc.collect()
return audio_save_path
video_to_audio_tab = gr.Interface(
fn=video_to_audio,
description=""" Video-to-Audio
NOTE: It takes longer to process high-resolution videos (>384 px on the shorter side).
Doing so does not improve results.
""",
inputs=[
gr.Video(),
gr.Text(label='Prompt'),
gr.Text(label='Negative prompt', value='music'),
gr.Number(label='Seed (-1: random)', value=-1, precision=0, minimum=-1),
gr.Number(label='Num steps', value=25, precision=0, minimum=1),
gr.Number(label='Guidance Strength', value=4.5, minimum=1),
gr.Number(label='Duration (sec)', value=8, minimum=1),
],
outputs='playable_video',
cache_examples=False,
title='Sonisphere - Sonic Branding Tool',
)
text_to_audio_tab = gr.Interface(
fn=text_to_audio,
description=""" Text-to-Audio
""",
inputs=[
gr.Text(label='Prompt'),
gr.Text(label='Negative prompt'),
gr.Number(label='Seed (-1: random)', value=-1, precision=0, minimum=-1),
gr.Number(label='Num steps', value=25, precision=0, minimum=1),
gr.Number(label='Guidance Strength', value=4.5, minimum=1),
gr.Number(label='Duration (sec)', value=8, minimum=1),
],
outputs='audio',
cache_examples=False,
title='Sonisphere - Sonic Branding Tool',
)
image_to_audio_tab = gr.Interface(
fn=image_to_audio,
description="""
Image-to-Audio
NOTE: It takes longer to process high-resolution images (>384 px on the shorter side).
Doing so does not improve results.
""",
inputs=[
gr.Image(type='filepath'),
gr.Text(label='Prompt'),
gr.Text(label='Negative prompt'),
gr.Number(label='Seed (-1: random)', value=-1, precision=0, minimum=-1),
gr.Number(label='Num steps', value=25, precision=0, minimum=1),
gr.Number(label='Guidance Strength', value=4.5, minimum=1),
gr.Number(label='Duration (sec)', value=8, minimum=1),
],
outputs='playable_video',
cache_examples=False,
title='Image-to-Audio Synthesis (experimental)',
)
if __name__ == "__main__":
parser = ArgumentParser()
parser.add_argument('--port', type=int, default=7860)
args = parser.parse_args()
gr.TabbedInterface([video_to_audio_tab, text_to_audio_tab, image_to_audio_tab],
['Video-to-Audio', 'Text-to-Audio', 'Image-to-Audio (experimental)']).launch(
server_name="0.0.0.0",
server_port=7860,
auth=("admin", "sonisphere"),
allowed_paths=[output_dir]) |