Spaces:
Running
Running
File size: 15,796 Bytes
9a33782 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 |
"""
Preview service for Video Model Studio
Handles the video generation logic and model integration
"""
import logging
import tempfile
import torch
from pathlib import Path
from typing import Dict, Any, List, Optional, Tuple, Callable
from vms.config import (
OUTPUT_PATH, STORAGE_PATH, MODEL_TYPES, TRAINING_PATH,
DEFAULT_PROMPT_PREFIX
)
from vms.utils import format_time
logger = logging.getLogger(__name__)
class PreviewingService:
"""Handles the video generation logic and model integration"""
def __init__(self):
"""Initialize the preview service"""
pass
def find_latest_lora_weights(self) -> Optional[str]:
"""Find the latest LoRA weights file"""
try:
lora_path = OUTPUT_PATH / "pytorch_lora_weights.safetensors"
if lora_path.exists():
return str(lora_path)
# If not found in the expected location, try to find in checkpoints
checkpoints = list(OUTPUT_PATH.glob("checkpoint-*"))
if not checkpoints:
return None
latest_checkpoint = max(checkpoints, key=lambda x: int(x.name.split("-")[1]))
lora_path = latest_checkpoint / "pytorch_lora_weights.safetensors"
if lora_path.exists():
return str(lora_path)
return None
except Exception as e:
logger.error(f"Error finding LoRA weights: {e}")
return None
def generate_video(
self,
model_type: str,
prompt: str,
negative_prompt: str,
prompt_prefix: str,
width: int,
height: int,
num_frames: int,
guidance_scale: float,
flow_shift: float,
lora_weight: float,
inference_steps: int,
enable_cpu_offload: bool,
fps: int
) -> Tuple[Optional[str], str, str]:
"""Generate a video using the trained model"""
try:
log_messages = []
def log(msg: str):
log_messages.append(msg)
logger.info(msg)
return "\n".join(log_messages)
# Find latest LoRA weights
lora_path = self.find_latest_lora_weights()
if not lora_path:
return None, "Error: No LoRA weights found", log("Error: No LoRA weights found in output directory")
# Add prefix to prompt
if prompt_prefix and not prompt.startswith(prompt_prefix):
full_prompt = f"{prompt_prefix}{prompt}"
else:
full_prompt = prompt
# Create correct num_frames (should be 8*k + 1)
adjusted_num_frames = ((num_frames - 1) // 8) * 8 + 1
if adjusted_num_frames != num_frames:
log(f"Adjusted number of frames from {num_frames} to {adjusted_num_frames} to match model requirements")
num_frames = adjusted_num_frames
# Get model type (internal name)
internal_model_type = MODEL_TYPES.get(model_type)
if not internal_model_type:
return None, f"Error: Invalid model type {model_type}", log(f"Error: Invalid model type {model_type}")
log(f"Generating video with model type: {internal_model_type}")
log(f"Using LoRA weights from: {lora_path}")
log(f"Resolution: {width}x{height}, Frames: {num_frames}, FPS: {fps}")
log(f"Guidance Scale: {guidance_scale}, Flow Shift: {flow_shift}, LoRA Weight: {lora_weight}")
log(f"Prompt: {full_prompt}")
log(f"Negative Prompt: {negative_prompt}")
# Import required components based on model type
if internal_model_type == "wan":
return self.generate_wan_video(
full_prompt, negative_prompt, width, height, num_frames,
guidance_scale, flow_shift, lora_path, lora_weight,
inference_steps, enable_cpu_offload, fps, log
)
elif internal_model_type == "ltx_video":
return self.generate_ltx_video(
full_prompt, negative_prompt, width, height, num_frames,
guidance_scale, flow_shift, lora_path, lora_weight,
inference_steps, enable_cpu_offload, fps, log
)
elif internal_model_type == "hunyuan_video":
return self.generate_hunyuan_video(
full_prompt, negative_prompt, width, height, num_frames,
guidance_scale, flow_shift, lora_path, lora_weight,
inference_steps, enable_cpu_offload, fps, log
)
else:
return None, f"Error: Unsupported model type {internal_model_type}", log(f"Error: Unsupported model type {internal_model_type}")
except Exception as e:
logger.exception("Error generating video")
return None, f"Error: {str(e)}", f"Exception occurred: {str(e)}"
def generate_wan_video(
self,
prompt: str,
negative_prompt: str,
width: int,
height: int,
num_frames: int,
guidance_scale: float,
flow_shift: float,
lora_path: str,
lora_weight: float,
inference_steps: int,
enable_cpu_offload: bool,
fps: int,
log_fn: Callable
) -> Tuple[Optional[str], str, str]:
"""Generate video using Wan model"""
start_time = torch.cuda.Event(enable_timing=True)
end_time = torch.cuda.Event(enable_timing=True)
try:
import torch
from diffusers import AutoencoderKLWan, WanPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video
log_fn("Importing Wan model components...")
# Use the smaller model for faster inference
model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
log_fn(f"Loading VAE from {model_id}...")
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
log_fn(f"Loading transformer from {model_id}...")
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
log_fn(f"Configuring scheduler with flow_shift={flow_shift}...")
pipe.scheduler = UniPCMultistepScheduler.from_config(
pipe.scheduler.config,
flow_shift=flow_shift
)
log_fn("Moving pipeline to CUDA device...")
pipe.to("cuda")
if enable_cpu_offload:
log_fn("Enabling model CPU offload...")
pipe.enable_model_cpu_offload()
log_fn(f"Loading LoRA weights from {lora_path} with weight {lora_weight}...")
pipe.load_lora_weights(lora_path)
pipe.fuse_lora(lora_weight)
# Create temporary file for the output
with tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) as temp_file:
output_path = temp_file.name
log_fn("Starting video generation...")
start_time.record()
output = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
num_frames=num_frames,
guidance_scale=guidance_scale,
num_inference_steps=inference_steps,
).frames[0]
end_time.record()
torch.cuda.synchronize()
generation_time = start_time.elapsed_time(end_time) / 1000 # Convert to seconds
log_fn(f"Video generation completed in {format_time(generation_time)}")
log_fn(f"Exporting video to {output_path}...")
export_to_video(output, output_path, fps=fps)
log_fn("Video generation and export completed successfully!")
# Clean up CUDA memory
pipe = None
torch.cuda.empty_cache()
return output_path, "Video generated successfully!", log_fn(f"Generation completed in {format_time(generation_time)}")
except Exception as e:
log_fn(f"Error generating video with Wan: {str(e)}")
# Clean up CUDA memory
torch.cuda.empty_cache()
return None, f"Error: {str(e)}", log_fn(f"Exception occurred: {str(e)}")
def generate_ltx_video(
self,
prompt: str,
negative_prompt: str,
width: int,
height: int,
num_frames: int,
guidance_scale: float,
flow_shift: float,
lora_path: str,
lora_weight: float,
inference_steps: int,
enable_cpu_offload: bool,
fps: int,
log_fn: Callable
) -> Tuple[Optional[str], str, str]:
"""Generate video using LTX model"""
start_time = torch.cuda.Event(enable_timing=True)
end_time = torch.cuda.Event(enable_timing=True)
try:
import torch
from diffusers import LTXPipeline
from diffusers.utils import export_to_video
log_fn("Importing LTX model components...")
model_id = "Lightricks/LTX-Video"
log_fn(f"Loading pipeline from {model_id}...")
pipe = LTXPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
log_fn("Moving pipeline to CUDA device...")
pipe.to("cuda")
if enable_cpu_offload:
log_fn("Enabling model CPU offload...")
pipe.enable_model_cpu_offload()
log_fn(f"Loading LoRA weights from {lora_path} with weight {lora_weight}...")
pipe.load_lora_weights(lora_path)
pipe.fuse_lora(lora_weight)
# Create temporary file for the output
with tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) as temp_file:
output_path = temp_file.name
log_fn("Starting video generation...")
start_time.record()
video = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
num_frames=num_frames,
guidance_scale=guidance_scale,
decode_timestep=0.03,
decode_noise_scale=0.025,
num_inference_steps=inference_steps,
).frames[0]
end_time.record()
torch.cuda.synchronize()
generation_time = start_time.elapsed_time(end_time) / 1000 # Convert to seconds
log_fn(f"Video generation completed in {format_time(generation_time)}")
log_fn(f"Exporting video to {output_path}...")
export_to_video(video, output_path, fps=fps)
log_fn("Video generation and export completed successfully!")
# Clean up CUDA memory
pipe = None
torch.cuda.empty_cache()
return output_path, "Video generated successfully!", log_fn(f"Generation completed in {format_time(generation_time)}")
except Exception as e:
log_fn(f"Error generating video with LTX: {str(e)}")
# Clean up CUDA memory
torch.cuda.empty_cache()
return None, f"Error: {str(e)}", log_fn(f"Exception occurred: {str(e)}")
def generate_hunyuan_video(
self,
prompt: str,
negative_prompt: str,
width: int,
height: int,
num_frames: int,
guidance_scale: float,
flow_shift: float,
lora_path: str,
lora_weight: float,
inference_steps: int,
enable_cpu_offload: bool,
fps: int,
log_fn: Callable
) -> Tuple[Optional[str], str, str]:
"""Generate video using HunyuanVideo model"""
start_time = torch.cuda.Event(enable_timing=True)
end_time = torch.cuda.Event(enable_timing=True)
try:
import torch
from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel, AutoencoderKLHunyuanVideo
from diffusers.utils import export_to_video
log_fn("Importing HunyuanVideo model components...")
model_id = "hunyuanvideo-community/HunyuanVideo"
log_fn(f"Loading transformer from {model_id}...")
transformer = HunyuanVideoTransformer3DModel.from_pretrained(
model_id,
subfolder="transformer",
torch_dtype=torch.bfloat16
)
log_fn(f"Loading pipeline from {model_id}...")
pipe = HunyuanVideoPipeline.from_pretrained(
model_id,
transformer=transformer,
torch_dtype=torch.float16
)
log_fn("Enabling VAE tiling for better memory usage...")
pipe.vae.enable_tiling()
log_fn("Moving pipeline to CUDA device...")
pipe.to("cuda")
if enable_cpu_offload:
log_fn("Enabling model CPU offload...")
pipe.enable_model_cpu_offload()
log_fn(f"Loading LoRA weights from {lora_path} with weight {lora_weight}...")
pipe.load_lora_weights(lora_path)
pipe.fuse_lora(lora_weight)
# Create temporary file for the output
with tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) as temp_file:
output_path = temp_file.name
log_fn("Starting video generation...")
start_time.record()
output = pipe(
prompt=prompt,
negative_prompt=negative_prompt if negative_prompt else None,
height=height,
width=width,
num_frames=num_frames,
guidance_scale=guidance_scale,
true_cfg_scale=1.0,
num_inference_steps=inference_steps,
).frames[0]
end_time.record()
torch.cuda.synchronize()
generation_time = start_time.elapsed_time(end_time) / 1000 # Convert to seconds
log_fn(f"Video generation completed in {format_time(generation_time)}")
log_fn(f"Exporting video to {output_path}...")
export_to_video(output, output_path, fps=fps)
log_fn("Video generation and export completed successfully!")
# Clean up CUDA memory
pipe = None
torch.cuda.empty_cache()
return output_path, "Video generated successfully!", log_fn(f"Generation completed in {format_time(generation_time)}")
except Exception as e:
log_fn(f"Error generating video with HunyuanVideo: {str(e)}")
# Clean up CUDA memory
torch.cuda.empty_cache()
return None, f"Error: {str(e)}", log_fn(f"Exception occurred: {str(e)}") |