MiniMax H3 Text-to-Video Workflow

This workflow is a local ComfyUI text-to-video setup for MiniMax H3. It turns one prompt into a cinematic video with synchronized visual and audio generation, making it useful for concept shots, short narrative clips, music-driven scenes, and fast model testing.

The workflow uses the MiniMax H3 local ComfyUI graph with the connected model, VAE, encoder, sampler, resolution, and video output chain shown in the JSON.

Main features:

- MiniMax H3 FL2VA diffusion model with the connected video VAE and Qwen3-VL text encoder
- Text-driven video generation with prompt control over shots, camera movement, dialogue, sound effects, and music
- Resolution Selector with a connected 16:9 widescreen route at the 0.8 megapixel setting
- 20-step simple scheduler with the res_multistep sampler route
- Duration input converted to a valid video frame length for the H3 frame-block requirement
- CreateVideo and SaveVideo nodes for a direct video output path
- Native audio-aware generation instead of adding a separate soundtrack afterward

Suggested workflow:

Load the MiniMax H3 model, video VAE, and Qwen3-VL encoder first. Write the visual action and audio direction in one prompt, choose the duration, then select the connected 16:9 resolution. Keep the sampler and scheduler settings stable while testing prompts; adjust duration and prompt structure before changing the model route.

⚡ RunningHub Workflow

Try the workflow online right now - no installation required.
👉 Workflow: https://www.runninghub.ai/post/2084544656423088130?inviteCode=rh-v1111

If the results meet your expectations, you can later deploy it locally for customization.

🎁 Fan Benefits: Register to get 1000 points + daily login 100 points - enjoy 4090 performance and 48 GB super power!

📵 Bilibili Updates (Mainland China & Asia-Pacific)

If you're in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown.
📵 Bilibili Video: https://www.bilibili.com/video/BV1MrMk69Ejk/

☕ Support Me on Ko-fi

If you find my content helpful and want to support future creations, you can buy me a coffee.
Every bit of support helps me keep creating.
👉 Ko-fi: https://ko-fi.com/aiksk

📬 Business Contact

For collaboration or inquiries, please contact aiksk95 on WeChat.

⚡ 打开下方链接即可在线体验，无需安装。
👉 工作流：https://www.runninghub.ai/post/2084544656423088130?inviteCode=rh-v1111

如果你觉得效果理想，也可以在本地进行自定义部署。

🎁 粉丝福利：注册即可领取 1000 积分，每日登录再领 100 积分，体验 4090 与 48 GB 超大显存性能。

📵 B站视频（中国大陆及亚洲地区）

如果你在中国大陆或亚洲地区，可以通过下面的视频查看工作流的实测效果与创作思路。
📵 B站视频：https://www.bilibili.com/video/BV1MrMk69Ejk/

我会在夸克网盘持续更新模型资源：
👉 https://pan.quark.cn/s/07bdc81784ce