metadata
license: apache-2.0
language:
- en
Gallery 路 GitHub 路 Blog 路 Paper 路 Discord
Gallery
For more demos and corresponding prompts, see the Allegro Gallery.
Key Feature
Allegro is capable of producing high-quality, 6-second videos at 30 frames per second and 720p resolution from simple text prompts.
Model info
| Model | Allegro |
|---|---|
| Description | Text-to-Video Diffusion Transformer |
| Download | <HF link - TBD> |
| Parameter | VAE: 175M |
| DiT: 2.8B | |
| Inference Precision | VAE: FP32/TF32/BF16/FP16 (best in FP32/TF32) |
| DiT/T5: BF16/FP32/TF32 | |
| Context Length | 79.2k |
| Resolution | 720 x 1280 |
| Frames | 88 |
| Video Length | 6 seconds @ 15 fps |
| Single GPU Memory Usage | 9.3G BF16 (with cpu_offload) |
Quick start
You can quickly get started with Allegro using the Hugging Face Diffusers library. For more tutorials, see Allegro GitHub (link-tbd).
Install necessary requirements:
pip install diffusers transformers imageio
Inference on single gpu:
from diffusers import DiffusionPipeline
import torch
allegro_pipeline = DiffusionPipeline.from_pretrained(
"rhythms-ai/allegro", trust_remote_code=True, torch_dtype=torch.bfloat16
).to("cuda")
allegro_pipeline.vae = allegro_pipeline.vae.to(torch.float32)
prompt = "a video of an astronaut riding a horse on mars"
positive_prompt = """
(masterpiece), (best quality), (ultra-detailed), (unwatermarked),
{}
emotional, harmonious, vignette, 4k epic detailed, shot on kodak, 35mm photo,
sharp focus, high budget, cinemascope, moody, epic, gorgeous
"""
negative_prompt = """
nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality,
low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.
"""
num_sampling_steps, guidance_scale, seed = 100, 7.5, 42
user_prompt = positive_prompt.format(args.user_prompt.lower().strip())
out_video = allegro_pipeline(
user_prompt,
negative_prompt=negative_prompt,
num_frames=88,
height=720,
width=1280,
num_inference_steps=num_sampling_steps,
guidance_scale=guidance_scale,
max_sequence_length=512,
generator = torch.Generator(device="cuda:0").manual_seed(seed)
).video[0]
imageio.mimwrite("test_video.mp4", out_video, fps=15, quality=8)
License
This repo is released under the Apache 2.0 License.