Text-to-Speech
Diffusers
Safetensors
GGUF
docker
comfyui
talking-face
lip-sync
live-avatar
music-generation
image-generation
video-generation
skill-pilot
Instructions to use skill-pilot/media-mcp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use skill-pilot/media-mcp with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("skill-pilot/media-mcp", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
tags:
|
|
|
|
| 4 |
- comfyui
|
| 5 |
- text-to-speech
|
| 6 |
- talking-face
|
|
@@ -14,7 +15,7 @@ tags:
|
|
| 14 |
|
| 15 |
# Skill Pilot Media Server
|
| 16 |
|
| 17 |
-
An all-in-one Media Server for Skill Pilot AI Agent
|
| 18 |
|
| 19 |
## Included Models and Tools
|
| 20 |
|
|
@@ -27,6 +28,21 @@ An all-in-one Media Server for Skill Pilot AI Agent **https://skill-pilot.ai**.
|
|
| 27 |
|
| 28 |
## How to Use
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
Free community support — no account required.
|
| 31 |
|
| 32 |
Join our Discord server for help, setup, tips, and updates. Find the invite link at **https://skill-pilot.ai**.
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
+
- docker
|
| 5 |
- comfyui
|
| 6 |
- text-to-speech
|
| 7 |
- talking-face
|
|
|
|
| 15 |
|
| 16 |
# Skill Pilot Media Server
|
| 17 |
|
| 18 |
+
An all-in-one Media Server for Skill Pilot AI Agent https://skill-pilot.ai. Includes ComfyUI for image/video generation, IndexTTS for text-to-speech, MuseTalk for talking video and live avatar, and SongBloom for music creation.
|
| 19 |
|
| 20 |
## Included Models and Tools
|
| 21 |
|
|
|
|
| 28 |
|
| 29 |
## How to Use
|
| 30 |
|
| 31 |
+
```bash
|
| 32 |
+
docker pull skillpilot/media-server:latest
|
| 33 |
+
docker run --gpus all \
|
| 34 |
+
-p 8188:8188 -p 7860:7860 -p 8080:8080 \
|
| 35 |
+
-p 3478:3478 -p 3478:3478/udp \
|
| 36 |
+
-p 5349:5349 -p 5349:5349/udp \
|
| 37 |
+
skillpilot/media-server:latest
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
The image is built on runpod/pytorch:2.4.0-py3.11-cuda12.4.1-devel-ubuntu22.04, ensuring compatibility with a wide range of NVIDIA GPUs and CUDA versions.
|
| 41 |
+
|
| 42 |
+
Tested on NVIDIA RTX 2060 GPU (12 GB VRAM) - MuseTalk live avatar can have real-time performance at 12 FPS.
|
| 43 |
+
|
| 44 |
+
Supports local GPU acceleration with NVIDIA drivers on the host machine or Runpod Cloud environments.
|
| 45 |
+
|
| 46 |
Free community support — no account required.
|
| 47 |
|
| 48 |
Join our Discord server for help, setup, tips, and updates. Find the invite link at **https://skill-pilot.ai**.
|