scenema-audio

ChrisColeTech/scenema-audio

scenema-audio is a text-to-audio model from ChrisColeTech. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. The card lists the license as other.

Downloads · 30 days

45% of all-time downloads

All-time downloads

113

Public

Repo size

21.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors13.1 GB · 61%

At a glance

Task: Text-to-Audio
License: other
Access: Public
Created: Aug 15, 2026
Updated: Aug 16, 2026
SHA: 304af501

Base models

ScenemaAI/scenema-audio

Model card

From the Hugging Face model README

Scenema Audio

Sample Audio - Honey Buns (30s)

~3.3 min on an RTX 5090 (32 GB)

Sample Audio - WAKE UP PEOPLE (2m)

~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
Text Encoder	`gemma-3-12b-it-Q4_K_M.gguf`	7.3 GB	Link
Audio Pipeline VAE	`scenema-audio-pipeline.safetensors`	6.71 GB	Link
Audio Encoder VAE	`scenema-audio-vae-encoder.safetensors`	42.7 MB	Link
Extras folder	`scenema-audio/extras`	2.3 GB	Link

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

Download extras folder Link 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

Use the workflow Link

Sources


Base model	ScenemaAI/scenema-audio

Task: Text-to-Audio
License: other
Created: Aug 15, 2026
Updated: Aug 16, 2026