pyramid-flow-sd3

[Paper] [Project Page ✨] [Code 🚀] [miniFLUX Model ⚡️] [demo 🤗]

This is the model repository for Pyramid Flow, a training-efficient Autoregressive Video Generation method based on Flow Matching. By training only on open-source datasets, it generates high-quality 10-second videos at 768p resolution and 24 FPS, and naturally supports image-to-video generation.

News

• 2024.10.29 ⚡️⚡️⚡️ We release training code and new model checkpoints with FLUX structure trained from scratch.

  We have switched the model structure from SD3 to a mini FLUX to fix human structure issues, please try our 1024p image checkpoint and 384p video checkpoint. We will release 768p video checkpoint in a few days.

• 2024.10.11 🤗🤗🤗 Hugging Face demo is available. Thanks @multimodalart for the commit!

• 2024.10.10 🚀🚀🚀 We release the technical report, project page and model checkpoint of Pyramid Flow.

Installation

We recommend setting up the environment with conda. The codebase currently uses Python 3.8.10 and PyTorch 2.1.2, and we are actively working to support a wider range of versions.

git clone https://github.com/jy0205/Pyramid-Flow
cd Pyramid-Flow

# create env using conda
conda create -n pyramid python==3.8.10
conda activate pyramid
pip install -r requirements.txt

Then, download the model from Huggingface (there are two variants: miniFLUX or SD3). The miniFLUX models support 1024p image and 384p video generation, and the SD3-based models support 768p and 384p video generation. The 384p checkpoint generates 5-second video at 24FPS, while the 768p checkpoint generates up to 10-second video at 24FPS.

from huggingface_hub import snapshot_download

model_path = 'PATH'   # The local directory to save downloaded checkpoint
snapshot_download("rain1011/pyramid-flow-sd3", local_dir=model_path, local_dir_use_symlinks=False, repo_type='model')

Usage

For inference, we provide Gradio demo, single-GPU, multi-GPU, and Apple Silicon inference code, as well as VRAM-efficient features such as CPU offloading. Please check our code repository for usage.

Below is a simplified two-step usage procedure. First, load the downloaded model:

import torch
from PIL import Image
from pyramid_dit import PyramidDiTForVideoGeneration
from diffusers.utils import load_image, export_to_video

torch.cuda.set_device(0)
model_dtype, torch_dtype = 'bf16', torch.bfloat16   # Use bf16 (not support fp16 yet)

model = PyramidDiTForVideoGeneration(
    'PATH',                                         # The downloaded checkpoint dir
    model_dtype,
    model_variant='diffusion_transformer_768p',     # 'diffusion_transformer_384p'
)

model.vae.enable_tiling()
# model.vae.to("cuda")
# model.dit.to("cuda")
# model.text_encoder.to("cuda")

# if you're not using sequential offloading bellow uncomment the lines above ^
model.enable_sequential_cpu_offload()

Then, you can try text-to-video generation on your own prompts:

prompt = "A movie trailer featuring the adventures of the 30 year old space man wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, vivid colors"

with torch.no_grad(), torch.cuda.amp.autocast(enabled=True, dtype=torch_dtype):
    frames = model.generate(
        prompt=prompt,
        num_inference_steps=[20, 20, 20],
        video_num_inference_steps=[10, 10, 10],
        height=768,
        width=1280,
        temp=16,                    # temp=16: 5s, temp=31: 10s
        guidance_scale=9.0,         # The guidance for the first frame, set it to 7 for 384p variant
        video_guidance_scale=5.0,   # The guidance for the other video latent
        output_type="pil",
        save_memory=True,           # If you have enough GPU memory, set it to `False` to improve vae decoding speed
    )

export_to_video(frames, "./text_to_video_sample.mp4", fps=24)

As an autoregressive model, our model also supports (text conditioned) image-to-video generation:

image = Image.open('assets/the_great_wall.jpg').convert("RGB").resize((1280, 768))
prompt = "FPV flying over the Great Wall"

with torch.no_grad(), torch.cuda.amp.autocast(enabled=True, dtype=torch_dtype):
    frames = model.generate_i2v(
        prompt=prompt,
        input_image=image,
        num_inference_steps=[10, 10, 10],
        temp=16,
        video_guidance_scale=4.0,
        output_type="pil",
        save_memory=True,           # If you have enough GPU memory, set it to `False` to improve vae decoding speed
    )

export_to_video(frames, "./image_to_video_sample.mp4", fps=24)

Usage tips

• The guidance_scale parameter controls the visual quality. We suggest using a guidance within [7, 9] for the 768p checkpoint during text-to-video generation, and 7 for the 384p checkpoint.
• The video_guidance_scale parameter controls the motion. A larger value increases the dynamic degree and mitigates the autoregressive generation degradation, while a smaller value stabilizes the video.
• For 10-second video generation, we recommend using a guidance scale of 7 and a video guidance scale of 5.

Gallery

The following video examples are generated at 5s, 768p, 24fp