Post5/21/2026, 11:22:13 PM
Stable Audio amazing at inpainting
You just give it reference audio, and it just uses that as the sample and generates a really well made song. Here are s…
Recent activity
144 totalPost5/21/2026, 3:05:18 PM
Stable-audio-3-medium support added
Just added support for the medium model. Note: the medium model only works on NVIDIA GPU | Model | Best for | Hardware …
Check-in5/21/2026, 3:56:49 AM
Confirmed on darwin · arm64 · apple m1 max
Commit messages (2)
Last by @cocktailpeanut•5/21/2026, 3:56:49 AM
Check-in5/21/2026, 3:55:54 AM
Confirmed on win32 · x64 · nvidia rtx a4500
Commit messages (2)
Last by @cocktailpeanut•5/21/2026, 3:56:49 AM
Post5/21/2026, 3:02:18 AM
Stable Audio 3 Small: Ultra Fast Music & Sound Effect Generation
What it doesn't do Stable Audio 3 does NOT generate songs with lyrics. What it does It generates: - Instrumental music …
Post5/19/2026, 1:46:11 AM
Java required?
Which platform is this supposed to work on? Tried on mac and it failed with: chsh -s /bin/zsh Diagnosis from AI:
Post5/18/2026, 5:39:07 AM
Seems to be deprecated, newer version here
According to the docs, this repo has been deprecated and now the work continues at https://github.com/geeknik/mmm
Post5/17/2026, 9:54:52 PM
Framepack testing
Because everything moves fast in the AI land, sometimes you forget that you do not need to be using the latest model to…
Post5/15/2026, 4:31:41 PM
DramaBox natural language prompting
What makes DramaBox interesting is the way you prompt. You prompt like you prompt a VIDEO GENERATION MODEL, in natural …
Post5/15/2026, 4:04:43 PM
Low VRAM Usage
Originally required huge VRAM to run this, but with the latest update you can now use this with low VRAM (I'm sure it w…
Check-in5/14/2026, 11:54:34 PM
Confirmed on win32 · x64 · nvidia rtx a4500
Commit messages (2)
pierrunoyt/dramabox-tts-pinokio—Implement installation notification and add launch script for DramaBox. Update install.js to notify users upon completion and create launch.py for starting the application. Enhance pinokio.json with title and description, and update README.md with new JavaScript and Curl usage examples.f791654
Last by @dimz•5/15/2026, 5:25:41 AM
Post5/13/2026, 11:01:43 PM
HiDream O1 Full FP8 Support
Just added support for FP8-FULL (previously only FP8-Dev was supported!) Commit: https://github.com/cocktailpeanut/hidr…
Post5/10/2026, 3:47:01 PM
Run HiDream-o1-image with Low VRAM (10GB)
This launcher lets you run the official web ui from the HiDream-o1-image project at https://github.com/HiDream-ai/HiDre…
Post5/10/2026, 3:38:28 PM
HiDream-O1-Image: a single transformer image generation model with reasoning skills
What is architecturally novel? HiDream-O1-Image is a single transformer that works directly on raw pixels. - no VAE - n…
Check-in5/10/2026, 3:12:23 PM
Confirmed on win32 · x64 · nvidia rtx a4500
Commit messages (2)
Last by @itouch44•5/10/2026, 10:25:21 PM
Post5/9/2026, 7:07:47 PM
ds4.c reasoning in action -- reasons better than me!
I tried some interesting questions to test the reasoning capabilities of deepseek4 (powered by ds4 ). Here's one image …
Post5/9/2026, 5:13:13 PM
ds4-webui: DeepSeek v4 Web UI for Apple Devices with 128GB+ memory
ds4-webui is a web ui for running DeepSeek V4 Flash locally through ds4.c From a user's point of view, it gives you a o…
Post5/9/2026, 4:31:33 AM
Overworld Low VRAM Word Model Simulator
Belated post on Overworld launcher--This app runs the Overworld Biome server, on NVIDIA GPU machines with at 8GB VRAM. …
Post5/8/2026, 4:23:48 AM
[Research] ds4 Models and System Requirements
ds4.c is a narrow Metal inference engine for DeepSeek V4 Flash. It is not a general GGUF runner and only supports the G…
Check-in5/7/2026, 9:42:21 PM
Confirmed on darwin · arm64 · apple m1 max
Commit messages (2)
Last by @cocktailpeanut•5/7/2026, 9:42:21 PM