T2V-Turbo-MS

<span style="font-family: 'Courier New', monospace; font-weight: bold">T2V-Turbo</span>: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

Model description 🚀

This repository contains unet_lora.pt that can turn ModelScopeT2V into our <span style="font-family: 'Courier New', monospace; font-weight: bold">T2V-Turbo</span> (MS). Our <span style="font-family: 'Courier New', monospace; font-weight: bold">T2V-Turbo</span> (MS) can achieve both fast and high-quality T2V generation. On VBench, the 4-step generation from our <span style="font-family: 'Courier New', monospace; font-weight: bold">T2V-Turbo</span> (MS) even outperform proprietary systems, including Gen-2 and Pika. Please refer to our GitHub repo for detailed instructions.

4-step Text-to-video Generation

<table class="center"> <td><video poster="" autoplay controls muted loop height="100%" playbackRate=2.0><source src="https://rg-lcd.s3.amazonaws.com/t2v-turbo-demo/t2v-turbo-ms/4_steps/0023.mp4" type="video/mp4"></video></td> <td><video poster="" autoplay controls muted loop height="100%" playbackRate=2.0><source src="https://rg-lcd.s3.amazonaws.com/t2v-turbo-demo/t2v-turbo-ms/4_steps/0026.mp4" type="video/mp4"></video></td> <td><video poster="" autoplay controls muted loop height="100%" playbackRate=2.0><source src="https://rg-lcd.s3.amazonaws.com/t2v-turbo-demo/t2v-turbo-ms/4_steps/0428.mp4" type="video/mp4"></video></td> <tr> <td style="text-align:center;" width="256">a dog wearing vr goggles on a boat</td> <td style="text-align:center;" width="256">Mickey Mouse is dancing on white background</td> <td style="text-align:center;" width="256">close-up shot, high detailed, A boy with a baseball cap, freckles, and a playful grin.</td> <tr> </table > <table class="center"> <td><video poster="" autoplay controls muted loop height="100%" playbackRate=2.0><source src="https://rg-lcd.s3.amazonaws.com/t2v-turbo-demo/t2v-turbo-ms/4_steps/0442.mp4" type="video/mp4"></video></td> <td><video poster="" autoplay controls muted loop height="100%" playbackRate=2.0><source src="https://rg-lcd.s3.amazonaws.com/t2v-turbo-demo/t2v-turbo-ms/4_steps/0158.mp4" type="video/mp4"></video></td> <td><video poster="" autoplay controls muted loop height="100%" playbackRate=2.0><source src="https://rg-lcd.s3.amazonaws.com/t2v-turbo-demo/t2v-turbo-ms/4_steps/0441.mp4" type="video/mp4"></video></td> <tr> <td style="text-align:center;" width="256">an old man with a long grey beard and green eyes, camera rotate anticlockwise</td> <td style="text-align:center;" width="256">The flowing water sparkled under the golden sunrise in a peaceful mountain river.</td> <td style="text-align:center;" width="256">close-up shot, high detailed, a girl with long curly blonde hair and sunglasses</td> <tr> <tr> </table >

Misuse, Malicious Use and Excessive Use 📖

Our model is meant for research purposes.

• It is prohibited to generate content that is demeaning or harmful to people or their environment, culture, religion, etc.
• Prohibited for pornographic, violent and bloody content generation.
• Prohibited for error and false information generation.