Skip to content

Commit c69d139

Browse files
mintlify[bot]comfyui-wiki
mintlify[bot]
and
comfyui-wiki
authored
Add HunyuanVideo 1.5 Documentation (#579)
* Update tutorials/video/hunyuan-video-1-5.mdx * Update tutorials/video/hunyuan-video-1-5.mdx * Update docs.json * Update zh-CN/tutorials/video/hunyuan-video-1-5.mdx * Refactor Hunyuan video documentation structure by removing outdated pages and reorganizing content into a new "Hunyuan" group. Update routing for Hunyuan video tutorials in both English and Chinese. This includes the deletion of old tutorial files and the addition of new routing entries for improved navigation. --------- Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> Co-authored-by: ComfyUI Wiki <[email protected]>
1 parent 4566a77 commit c69d139

File tree

5 files changed

+136
-2
lines changed

5 files changed

+136
-2
lines changed

‎docs.json‎

Lines changed: 23 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -154,7 +154,6 @@
154154
"group": "Video",
155155
"pages": [
156156
"tutorials/video/ltxv",
157-
"tutorials/video/hunyuan-video",
158157
{
159158
"group": "Wan Video",
160159
"pages": [
@@ -179,6 +178,13 @@
179178
}
180179
]
181180
},
181+
{
182+
"group": "Hunyuan",
183+
"pages": [
184+
"tutorials/video/hunyuan/hunyuan-video",
185+
"tutorials/video/hunyuan/hunyuan-video-1-5"
186+
]
187+
},
182188
{
183189
"group": "Cosmos",
184190
"pages": [
@@ -760,7 +766,6 @@
760766
"group": "视频",
761767
"pages": [
762768
"zh-CN/tutorials/video/ltxv",
763-
"zh-CN/tutorials/video/hunyuan-video",
764769
{
765770
"group": "万相视频",
766771
"pages": [
@@ -785,6 +790,14 @@
785790
}
786791
]
787792
},
793+
794+
{
795+
"group": "腾讯混元",
796+
"pages": [
797+
"tutorials/video/hunyuan/hunyuan-video",
798+
"tutorials/video/hunyuan/hunyuan-video-1-5"
799+
]
800+
},
788801
{
789802
"group": "Cosmos",
790803
"pages": [
@@ -1398,6 +1411,14 @@
13981411
{
13991412
"source": "/zh-CN/built-in-nodes/api-nodes/:slug*",
14001413
"destination": "/zh-CN/built-in-nodes/partner-node/:slug*"
1414+
},
1415+
{
1416+
"source": "/tutorials/video/hunyuan-video",
1417+
"destination": "/tutorials/video/hunyuan/hunyuan-video"
1418+
},
1419+
{
1420+
"source": "/zh-CN/tutorials/video/hunyuan-video",
1421+
"destination": "/zh-CN/tutorials/video/hunyuan/hunyuan-video"
14011422
}
14021423
]
14031424
}

‎tutorials/video/hunyuan/hunyuan-video-1-5.mdx‎

Lines changed: 56 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,56 @@
1+
---
2+
title: "HunyuanVideo 1.5"
3+
description: "Learn how to use HunyuanVideo 1.5, a lightweight 8.3B parameter model for high-quality video generation on consumer GPUs"
4+
sidebarTitle: "HunyuanVideo 1.5"
5+
---
6+
7+
import UpdateReminder from "/snippets/tutorials/update-reminder.mdx";
8+
9+
[HunyuanVideo 1.5](https://github.com/Tencent/HunyuanVideo) is a lightweight 8.3B parameter model developed by Tencent's Hunyuan team. It delivers flagship-quality video generation on consumer GPUs (24GB VRAM), dramatically lowering the barrier to entry without compromising on quality.
10+
11+
<UpdateReminder/>
12+
13+
## Model highlights
14+
15+
- **Compact powerhouse**: Delivers SOTA performance comparable to larger models while running on consumer hardware.
16+
- **Versatile generation**: Supports high-quality Text-to-Video and Image-to-Video (5-10s) with exceptional consistency.
17+
- **Precise control**: Strong instruction following for camera movements, physics, and emotional expressions.
18+
- **Cinematic quality**: Native 720p output (upscalable to 1080p) with professional aesthetics.
19+
- **Rich features**: Supports diverse styles (realistic, anime, 3D) and in-video text rendering (Chinese/English).
20+
21+
## Workflow templates
22+
23+
[video_hunyuan_video_1.5_720p_i2v.json](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_hunyuan_video_1.5_720p_i2v.json)
24+
25+
[video_hunyuan_video_1.5_720p_t2v.json](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_hunyuan_video_1.5_720p_t2v.json)
26+
27+
## Model links
28+
**text_encoders**
29+
30+
- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)
31+
- [byt5_small_glyphxl_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/byt5_small_glyphxl_fp16.safetensors)
32+
33+
**diffusion_models**
34+
35+
- [hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/diffusion_models/hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors)
36+
- [hunyuanvideo1.5_720p_t2v_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/diffusion_models/hunyuanvideo1.5_720p_t2v_fp16.safetensors)
37+
38+
**vae**
39+
40+
- [hunyuanvideo15_vae_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/vae/hunyuanvideo15_vae_fp16.safetensors)
41+
42+
43+
Model Storage Location
44+
45+
```
46+
:open_file_folder: ComfyUI/
47+
├── :open_file_folder: models/
48+
│ ├── :open_file_folder: text_encoders/
49+
│ │ ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
50+
│ │ └── byt5_small_glyphxl_fp16.safetensors
51+
│ ├── :open_file_folder: diffusion_models/
52+
│ │ ├── hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors
53+
│ │ └── hunyuanvideo1.5_720p_t2v_fp16.safetensors
54+
│ └── :open_file_folder: vae/
55+
│ └── hunyuanvideo15_vae_fp16.safetensors
56+
```

tutorials/video/hunyuan-video.mdx renamed to tutorials/video/hunyuan/hunyuan-video.mdx

File renamed without changes.

‎zh-CN/tutorials/video/hunyuan/hunyuan-video-1-5.mdx‎

Lines changed: 57 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,57 @@
1+
---
2+
title: "混元视频 1.5 ComfyUI 教程"
3+
description: "了解如何使用混元视频 1.5，一个轻量级的 8.3B 参数模型，可在消费级 GPU 上生成高质量视频"
4+
sidebarTitle: "混元视频 1.5"
5+
---
6+
7+
import UpdateReminder from "/snippets/tutorials/update-reminder.mdx";
8+
9+
混元视频 1.5是由腾讯混元团队开发的轻量级 8.3B 参数模型。它可在消费级 GPU（24GB 显存）上提供旗舰级质量的视频生成，大幅降低了使用门槛，同时不影响质量。
10+
11+
## 模型亮点
12+
13+
- **小巧强大**：在消费级硬件上运行的同时，提供与大型模型相当的 SOTA 性能。
14+
- **多功能生成**：支持高质量的文本生成视频和图像生成视频（5-10秒），具有出色的一致性。
15+
- **精确控制**：对镜头运动、物理效果和情感表达有强大的指令遵循能力。
16+
- **电影级质量**：原生 720p 输出（可升级至 1080p），具有专业美学效果。
17+
- **丰富功能**：支持多种风格（写实、动漫、3D）和视频内文字渲染（中文/英文）。
18+
19+
<UpdateReminder/>
20+
21+
## 模型链接
22+
23+
**text_encoders**
24+
25+
- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)
26+
- [byt5_small_glyphxl_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/byt5_small_glyphxl_fp16.safetensors)
27+
28+
**diffusion_models**
29+
30+
- [hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/diffusion_models/hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors)
31+
- [hunyuanvideo1.5_720p_t2v_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/diffusion_models/hunyuanvideo1.5_720p_t2v_fp16.safetensors)
32+
33+
**vae**
34+
35+
- [hunyuanvideo15_vae_fp16.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/vae/hunyuanvideo15_vae_fp16.safetensors)
36+
37+
38+
Model Storage Location
39+
40+
```
41+
:open_file_folder: ComfyUI/
42+
├── :open_file_folder: models/
43+
│ ├── :open_file_folder: text_encoders/
44+
│ │ ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
45+
│ │ └── byt5_small_glyphxl_fp16.safetensors
46+
│ ├── :open_file_folder: diffusion_models/
47+
│ │ ├── hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors
48+
│ │ └── hunyuanvideo1.5_720p_t2v_fp16.safetensors
49+
│ └── :open_file_folder: vae/
50+
│ └── hunyuanvideo15_vae_fp16.safetensors
51+
```
52+
53+
## 工作流
54+
55+
[video_hunyuan_video_1.5_720p_i2v.json](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_hunyuan_video_1.5_720p_i2v.json)
56+
57+
[video_hunyuan_video_1.5_720p_t2v.json](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_hunyuan_video_1.5_720p_t2v.json)

zh-CN/tutorials/video/hunyuan-video.mdx renamed to zh-CN/tutorials/video/hunyuan/hunyuan-video.mdx

File renamed without changes.

0 commit comments

Comments
 (0)