forked from camenduru/text-to-video-synthesis-colab
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
94 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,94 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": { | ||
"id": "view-in-github" | ||
}, | ||
"source": [ | ||
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/camenduru/text-to-video-synthesis-colab/blob/main/potat1_text_to_video_diffusers.ipynb)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"#https://github.com/huggingface/diffusers/pull/2738 modified\n", | ||
"!pip install git+https://github.com/huggingface/diffusers transformers accelerate imageio[ffmpeg] -U\n", | ||
"!pip install -q torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 torchtext==0.14.1 torchdata==0.5.1 --extra-index-url https://download.pytorch.org/whl/cu116 -U" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": { | ||
"id": "n2ibl97e2yM4" | ||
}, | ||
"outputs": [], | ||
"source": [ | ||
"import torch\n", | ||
"from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler\n", | ||
"from diffusers.utils import export_to_video\n", | ||
"from IPython.display import HTML\n", | ||
"from base64 import b64encode\n", | ||
"import datetime\n", | ||
"\n", | ||
"pipe = DiffusionPipeline.from_pretrained(\"camenduru/potat1\", torch_dtype=torch.float16)\n", | ||
"pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)\n", | ||
"pipe.enable_model_cpu_offload()\n", | ||
"pipe.enable_vae_slicing()\n", | ||
"\n", | ||
"!mkdir /content/videos" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"prompt = 'Darth Vader surfing a wave' #@param {type:\"string\"}\n", | ||
"negative_prompt = \"low quality\" #@param {type:\"string\"}\n", | ||
"num_frames = 30 #@param {type:\"raw\"}\n", | ||
"video_frames = pipe(prompt, negative_prompt=negative_prompt, width=1024, height=576, num_inference_steps=25, num_frames=num_frames).frames\n", | ||
"output_video_path = export_to_video(video_frames)\n", | ||
"\n", | ||
"new_video_path = f'/content/videos/{datetime.datetime.now().strftime(\"%Y-%m-%d_%H:%M:%S\")}.mp4'\n", | ||
"!ffmpeg -y -i {output_video_path} -c:v libx264 -c:a aac -strict -2 {new_video_path} >/dev/null 2>&1\n", | ||
"\n", | ||
"print(output_video_path, '->', new_video_path)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"!cp {new_video_path} /content/videos/tmp.mp4\n", | ||
"mp4 = open('/content/videos/tmp.mp4','rb').read()\n", | ||
"\n", | ||
"decoded_vid = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n", | ||
"HTML(f'<video width=400 controls><source src=\"{decoded_vid}\" type=\"video/mp4\"></video>')" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"accelerator": "GPU", | ||
"colab": { | ||
"provenance": [] | ||
}, | ||
"gpuClass": "standard", | ||
"kernelspec": { | ||
"display_name": "Python 3", | ||
"name": "python3" | ||
}, | ||
"language_info": { | ||
"name": "python" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 0 | ||
} |