Instructions to use ChrisColeTech/scenema-audio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ChrisColeTech/scenema-audio with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ChrisColeTech/scenema-audio:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ChrisColeTech/scenema-audio:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ChrisColeTech/scenema-audio:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ChrisColeTech/scenema-audio:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ChrisColeTech/scenema-audio:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ChrisColeTech/scenema-audio:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ChrisColeTech/scenema-audio:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ChrisColeTech/scenema-audio:Q4_K_M

Use Docker

docker model run hf.co/ChrisColeTech/scenema-audio:Q4_K_M

LM Studio
Jan
Ollama
How to use ChrisColeTech/scenema-audio with Ollama:
```
ollama run hf.co/ChrisColeTech/scenema-audio:Q4_K_M
```

Unsloth Studio

How to use ChrisColeTech/scenema-audio with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ChrisColeTech/scenema-audio to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ChrisColeTech/scenema-audio to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ChrisColeTech/scenema-audio to start chatting

Docker Model Runner
How to use ChrisColeTech/scenema-audio with Docker Model Runner:
```
docker model run hf.co/ChrisColeTech/scenema-audio:Q4_K_M
```

Lemonade

How to use ChrisColeTech/scenema-audio with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ChrisColeTech/scenema-audio:Q4_K_M

Run and chat with the model

lemonade run user.scenema-audio-Q4_K_M

List all available models

lemonade list

Atomic Chat

scenema-audio / README.md

ChrisColeTech

Update README.md

90bd201 verified 3 days ago

preview code

Raw

History Blame Contribute Delete

2.72 kB

	---
	license: other
	pipeline_tag: text-to-audio
	tags:
	- text-to-music
	- music-generation
	- ltxv

	base_model:
	- ScenemaAI/scenema-audio
	---

	# Scenema Audio

	---

	## Sample Audio - Honey Buns (30s)

	<audio controls src="https://huggingface.co/ChrisColeTech/scenema-audio/resolve/main/samples/ComfyUI_00024.mp3"></audio>

	- ~3.3 min on an RTX 5090 (32 GB)


	## Sample Audio - WAKE UP PEOPLE (2m)

	<audio controls src="https://huggingface.co/ChrisColeTech/scenema-audio/resolve/main/samples/ComfyUI_00030.mp3"></audio>

	- ~4.3 min on an RTX 5090 (32 GB)

	## Components used to generate

	\| Component \| File \| ~Size \| Download \|
	\|---\|---\|---\|---\|
	\| Transformer \| `scenema-audio-transformer-int8.safetensors` \| 4.91 GB \| [Link](https://huggingface.co/ChrisColeTech/scenema-audio/blob/main/split/diffusion_models/scenema-audio-transformer-int8.safetensors) \|
	\| Text Encoder \| `gemma-3-12b-it-Q4_K_M.gguf` \| 7.3 GB \| [Link](https://huggingface.co/ChrisColeTech/scenema-audio/blob/main/split/text_encoders/gemma-3-12b-it-Q4_K_M.gguf) \|
	\| Audio Pipeline VAE \| `scenema-audio-pipeline.safetensors` \| 6.71 GB \| [Link](https://huggingface.co/ChrisColeTech/scenema-audio/blob/main/split/vae/scenema-audio-pipeline.safetensors) \|
	\| Audio Encoder VAE \| `scenema-audio-vae-encoder.safetensors` \| 42.7 MB \| [Link](https://huggingface.co/ChrisColeTech/scenema-audio/blob/main/split/vae/scenema-audio-vae-encoder.safetensors) \|
	\| Extras folder \| `scenema-audio/extras` \| 2.3 GB \| [Link](https://huggingface.co/ChrisColeTech/scenema-audio/tree/main/extras)

	⚠ scenema-audio extras is required for longer audio, and for voice-to-voice ⚠

	- Download extras folder [Link](https://huggingface.co/ChrisColeTech/scenema-audio/tree/main/extras) and place here: /ComfyUI/models/scenema-audio/extras
	- Create the `scenema-audio/extras` folder if it doesnt exist

	Must have:
	- /scenema-audio/extras/mel-band-roformer
	- /scenema-audio/extras/bigvgan
	- /scenema-audio/extras/campplus
	- /scenema-audio/extras/seedvc
	- /scenema-audio/extras/whisper-small

	---

	## ⚠ Must use the updated GGUF Loader ⚠

	In comfy:
	- Open the ComfyUI Manager
	- Change the channel to "Channel (remote)"
	- and search for comfyui-gguf-loader

	![image](https://cdn-uploads.huggingface.co/production/uploads/6a550d1dc84594e3ada10828/SgiBz44CKsKT5m2sCXDnB.png)


	Use the workflow [Link](https://huggingface.co/ChrisColeTech/scenema-audio/blob/main/workflow_examples/scenema_audio.json)

	![image](https://huggingface.co/ChrisColeTech/scenema-audio/resolve/main/workflow_examples/workflow_example_scenema.png)

	---

	## Sources

	\| \| \|
	\|---\|---\|
	\| Base model \| [ScenemaAI/scenema-audio](https://huggingface.co/ScenemaAI/scenema-audio) \|