Download
1 variant available
9180 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
880 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1010 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(90)
Jan 18, 2025
Hunyuan Video
First, read the instructions.
This is the integrated video version of the tiktok - style LoRA.
This is a LoRA model in the short - video style. Through the intelligent algorithms of short - video platforms, it has selected beauties and handsome men that are more in line with the aesthetic preferences of Chinese people. At the same time, the images generated by this model are more suitable for generating videos from images, and they are more in line with the aesthetics of short - videos. Don't you think so? This version focuses on enhancing the learning of facial features, body shapes, skin colors, and the Douyin style.
This model has selected 500 popular short - videos from the past two years (varying from person to person) to obtain the training set.
Trigger word: dygirl short - video style,It supports both Chinese and English. Degradation is a problem that exists in current video models and needs to be solved by trial - and - error. At the same time, let's cheer for the arrival of the 1.5 era of videos. I believe that 2025 will be a year of explosive growth for AI - related videos!
The example images are all tags reverse - derived from images not in the training set. The prompt words are in the "Display Text" node. Click on the example image, view the workflow, and find the "Display Text" node. This version is recommended to use ComfyUI to achieve the best results.
Show more
1210 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5810 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Tencent Hunyuan is licensed under the Tencent Hunyuan Community License Agreement, Copyright © 2024 Tencent. All Rights Reserved. The trademark rights of “Tencent Hunyuan” are owned by Tencent or its affiliate.
Powered by Tencent Hunyuan
Read the description first
This is the lora version of thirst trap girl, still free to download.
This is a short video style lora model, after the short video platform intelligent algorithms screened out more suitable for the national aesthetic beauty and handsome, while the model out of the figure is also more suitable for use in the Tusheng video, more in line with the aesthetic of the short video, you say is it.
This version focuses on enhancing the learning of face, body type, skin color, and jitterbug style.
You can either fill in the trigger word or dygirl.
This model has screened 500 popular short videos in the past two years (varies from person to person), and the last remaining 100 videos for frame extraction. Most of them use 3-5 frames/second for extraction, eliminating the vignette and the interference part of the picture, and then repairing the hand of each picture (dynamic frame hand is almost always blurred) to arrive at the training set (in order to ensure the training effect, the same person's picture are censored).
This version basically solves the problem of hand degradation in the distillation model, but the training set is obtained by extracting frames and repairing hands, so it is inevitable that there are some defects.
The example graphs are all non-training set of graph backpropagation tags, cue words in the node “show text”. Click on the example graph, check the workflow, and find the show text node.
This version recommends using comfyui for best results.