MiniMax-H3 4-Step FlashGen LoRA
⚡
46
4-step text-to-video+audio with MiniMax-H3 FlashGen LoRA
🏗️ Building on HF
PRASHANT G
prashant-AI-ML
AI & ML interests
Natural Language Processing, Text Generation, Large Language Models, Quantization, Fine-Tuning, Model Merging
Recent Activity
liked a Space about 7 hours ago
hugging-apps/minimax-h3-flashgen-4step liked a Space 5 days ago
techfreakworm/qwen-voice-studio liked a Space 6 days ago
hugging-apps/oraclezoom-super-resolutionOrganizations
liked a
Space about 7 hours ago
liked a
Space 5 days ago
liked a
Space 6 days ago
liked a
Space 11 days ago
liked a
Space 14 days ago
upvoted an article 25 days ago
Article
Wire It, Run It, Deploy It: AI Workflows in Gradio
ysharma, abidlabs
• • 48 liked a
Space 27 days ago
liked 6
Spaces about 1 month ago
MiniMax H3
🎬
109
Video generation with a synchronized soundtrack
MiniMax-H3 Ultra Fast
⚡
6
Ultra-fast local NVFP4 video + synchronized audio generation
LTX 2.5
⚡
28
Generate videos from text prompts (optional image)
SCoPE Camera Controlled Video
🎥
14
Steer a 3D camera path through any still image
PlagueKind MiniMax H3
🦊
8
The PlagueKind V1.5 workflow for MiniMax-H3 video + audio
MiniMax-H3 Ultra Fast
⚡
249
Ultra-fast local NVFP4 video + synchronized audio generation
updated a
Space 2 months ago
upvoted a changelog 2 months ago
Hugging Face Changelog
Build Spaces with AI Agents
• 170
reacted to NatalieY's post with 👀🔥👍 2 months ago
Post
2462
Aiden: a physical AI agent that controls phones over USB HID
Most GUI agent work assumes the agent lives inside the device or
drives it through a debugging interface. We went the other way.
Aiden is a small board that sits outside the host. It captures the
screen over HDMI-to-CSI, runs the agent loop on-device, and sends
actions back as a standard USB HID device — the host sees a keyboard
and a mouse, nothing else. No app install, no root, no ADB, no cloud.
Runtime is Go. Frame capture, full-duplex audio with VAD, the agent
loop, and HID output all run as independent goroutines. There's no
backend — nothing leaves the device, which is the only defensible
design when the input is a live feed of someone's phone screen.
Open questions we haven't solved:
· Action verification — inferring success from a re-read of the
screen breaks when loading states lie
· Prompt injection — an agent that reads screens reads whatever an
attacker puts on them
· iOS pointer control requires AssistiveTouch
Repo, including the HID gadget config and capture pipeline:
github.com/AidenAI-IO/aiden-hardware-demo
Wrote up how this differs from cloud-based computer use agents here:
https://aidenai.io/blog/mobile-ai-agent-vs-computer-use-agent-whats-the-difference/
Note: current hardware is a dev board, not a finished product.
Most GUI agent work assumes the agent lives inside the device or
drives it through a debugging interface. We went the other way.
Aiden is a small board that sits outside the host. It captures the
screen over HDMI-to-CSI, runs the agent loop on-device, and sends
actions back as a standard USB HID device — the host sees a keyboard
and a mouse, nothing else. No app install, no root, no ADB, no cloud.
Runtime is Go. Frame capture, full-duplex audio with VAD, the agent
loop, and HID output all run as independent goroutines. There's no
backend — nothing leaves the device, which is the only defensible
design when the input is a live feed of someone's phone screen.
Open questions we haven't solved:
· Action verification — inferring success from a re-read of the
screen breaks when loading states lie
· Prompt injection — an agent that reads screens reads whatever an
attacker puts on them
· iOS pointer control requires AssistiveTouch
Repo, including the HID gadget config and capture pipeline:
github.com/AidenAI-IO/aiden-hardware-demo
Wrote up how this differs from cloud-based computer use agents here:
https://aidenai.io/blog/mobile-ai-agent-vs-computer-use-agent-whats-the-difference/
Note: current hardware is a dev board, not a finished product.
- 3 replies
liked 2
models 3 months ago
