v3.4.0 - ACE Step Audio XL

v3.4.0 - ACE Step Audio v1.5 XL

The ACE Step Audio v1.5 XL pipeline introduces advanced, high-fidelity text-to-music generation directly into the application. Leveraging an expanded "XL" model architecture, it significantly improves structural coherence, produces cleaner instrumentation, and adheres more accurately to complex genre prompts or lyrics. This upgrade allows creators to generate complete, professional-grade musical tracks from simple text inputs, serving as a powerful local engine for independent audio production.

New Features

1. ACE Step Audio v1.5 XL (Text-to-Music)
2. VideoEditor Audio Support

---

2026-05-16.09-25-47.mp4

---

Installation

This dev build is NOT compatible with previous versions of Amuse or existing ONNX models, full uninstall of Amuse 3.2.0 is REQUIRED.

Upgrade from v3.3.2, v3.3.3, v3.3.4, v3.3.5, v3.3.7 is supported

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

• New Install & Upgrade:
  1. Download and run Amuse_vX.X.X.exe.
  2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
2. Run Amuse.exe.

Upgrade:

1. Download and extract Amuse_vX.X.X.zip to a temp folder.
2. Copy and overwrite all files in your existing location
3. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.

---

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

• NVIDIA: Supports all CUDA compatible devices (CUDA 12.8).
• AMD: Supports Radeon 7000 GPUs (ROCm 7.2.1).
• Intel: Not Supported.
• Legacy Hardware: If you are using an incompatible device or older AMD hardware, it is highly recommended to stay on v3.2.0 until broader support is ported to the new engine.

---

Developers Note

Only install this version if you are interested in testing development builds. As I am a solo developer with very limited testing resources and only a few devices, things may not work, and features may be missing. Each dev build may require re-installs and other manual processes. Please only install if this is okay; otherwise, wait until a stable release is ready.

Full Changelog: v3.3.7...v3.4.0

v3.3.7 - Video Timeline Editor

v3.3.7 - Video Timeline Editor

The new Video Timeline Editor provides a frame-accurate workspace designed specifically for sequencing and refining AI-generated clips. By establishing a consistent canvas based on your first import, the editor ensures seamless transitions by automatically center-cropping subsequent footage to match the primary width, height, and framerate.

Use the Split and Trim tools to isolate your best moments, or leverage the Extend and Copy functions to perfect your timing. With customizable preview qualities and adjustable frame scales, you can maintain a fluid editing workflow even when handling high-resolution assets, giving you granular control over the final structure of your AI video projects.

---

2026-05-07.19-19-26.mp4

---

Installation

This dev build is NOT compatible with previous versions of Amuse or existing ONNX models, full uninstall of Amuse 3.2.0 is REQUIRED.

Upgrade from v3.3.2, v3.3.3, v3.3.4, v3.3.5 is supported

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

• New Install & Upgrade:
  1. Download and run Amuse_vX.X.X.exe.
  2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
2. Run Amuse.exe.

Upgrade:

1. Download and extract Amuse_vX.X.X.zip to a temp folder.
2. Copy and overwrite all files in your existing location
3. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.

---

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

• NVIDIA: Supports all CUDA compatible devices (CUDA 12.8).
• AMD: Supports Radeon 7000 GPUs (ROCm 7.2.1).
• Intel: Not Supported.
• Legacy Hardware: If you are using an incompatible device or older AMD hardware, it is highly recommended to stay on v3.2.0 until broader support is ported to the new engine.

---

Developers Note

Only install this version if you are interested in testing development builds. As I am a solo developer with very limited testing resources and only a few devices, things may not work, and features may be missing. Each dev build may require re-installs and other manual processes. Please only install if this is okay; otherwise, wait until a stable release is ready.

Full Changelog: v3.3.5...v3.3.7

v3.3.5 - Video & Interface Upgrades

v3.3.5 - Video & Interface Upgrades

This update brings significant under-the-hood performance improvements, expanded video processing capabilities, and UI refinements to enhance your workflow.

FirstFrame & LastFrame

Native support has been added for FirstFrame and LastFrame operations.
These functions are specifically optimized for LTX and WAN models, allowing for greater precision and control in your video generation pipelines.

Transformers v5

We have updated the core engine to support Transformers v5.
This ensures full compatibility with the latest Hugging Face ecosystem updates, providing better performance, stability, and access to the newest model architectures.

VideoFrame Viewer

Seamlessly extract specific frames from your videos for further processing or reference, removing the need for external tools.

2026-04-30.15-38-16.mp4

---

Installation

This dev build is NOT compatible with previous versions of Amuse or existing ONNX models, full uninstall of Amuse 3.2.0 is REQUIRED.

Upgrade from v3.3.2, v3.3.3, v3.3.4 is supported,
Environments will be updated this version, Settings file Reset

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

• New Install & Upgrade:
  1. Download and run Amuse_vX.X.X.exe.
  2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
2. Run Amuse.exe.

Upgrade:

1. Download and extract Amuse_vX.X.X.zip to a temp folder.
2. Copy and overwrite all files in your existing location
3. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.

---

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

• NVIDIA: Supports all CUDA compatible devices (CUDA 12.8).
• AMD: Supports Radeon 7000, 9000 series GPUs (ROCm 7.2.1).
• Intel: Not Supported.
• Legacy Hardware: If you are using an incompatible device or older AMD hardware, it is highly recommended to stay on v3.2.0 until broader support is ported to the new engine.

---

Developers Note

Only install this version if you are interested in testing development builds. As I am a solo developer with very limited testing resources and only a few devices, things may not work, and features may be missing. Each dev build may require re-installs and other manual processes. Please only install if this is okay; otherwise, wait until a stable release is ready.

Full Changelog: v3.3.4...v3.3.5

v3.3.4 - ImageEdit Improvements

ImageEdit Improvements

Expanding the ImageEdit toolkit with selection tools and FLUX.2 Klein integration.

FrameToFrame Video Processing

You can now process videos frame-by-frame. This feature utilizes ImageEdit models, including FLUX.2 Klein, to apply consistent AI transformations across video sequences.

Selection and Masking Tools

We have added new tools to the ImageEdit section to give you better control over your projects:

• Selection Tool: Define specific areas for the AI to process.
• Masking Tool: Paint over areas you want to modify while keeping the rest of the image unchanged.

FLUX.2 Klein Inpaint Support

Full support for FLUX.2 Klein inpainting is now available. This allows for high-quality object removal or content generation within masked areas, designed to match the lighting and style of the original image.

Improved Settings Area

The Settings section has been reorganized to be more user-friendly. It is now easier to manage your model paths, hardware configuration, and performance options.

---

2026-04-26.13-08-45.mp4

Installation

This dev build is NOT compatible with previous versions of Amuse or existing ONNX models, full uninstall of Amuse 3.0 is REQUIRED.

Upgrade from v3.3.2, v3.3.3 is supported,
$\color{red}{\text{WARNING: Environments will be rebuilt this version (Diffusers Update).}}$

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

• New Install & Upgrade:
  1. Download and run Amuse_vX.X.X.exe.
  2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
2. Run Amuse.exe.

Upgrade:

1. Download and extract Amuse_vX.X.X.zip to a temp folder.
2. Copy and overwrite all files in your existing location
3. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.

---

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

• NVIDIA: Supports all CUDA compatible devices (CUDA 12.8).
• AMD: Supports Radeon 7000, 9000 series GPUs (ROCm 7.2.1).
• Intel: Not Supported.
• Legacy Hardware: If you are using an incompatible device or older AMD hardware, it is highly recommended to stay on v3.2.0 until broader support is ported to the new engine.

---

Developers Note

Only install this version if you are interested in testing development builds. As I am a solo developer with very limited testing resources and only a few devices, things may not work, and features may be missing. Each dev build may require re-installs and other manual processes. Please only install if this is okay; otherwise, wait until a stable release is ready.

Full Changelog: v3.3.3...v3.3.4

v3.3.3 - Automations

v3.3.3 - Automations

Amuse now supports Automations, allowing you to move beyond single-image generation into high-volume workflows. Whether you're stress-testing a new model with a Seed Batch or processing an entire library of videos, the new Automation engine handles the heavy lifting.

Supported Automation Modes

• Seed Batch: Perfect for finding the "Golden Seed." Generates a specified number of outputs using a unique random seed for each iteration.
• Prompt Lines: Feed Amuse a single .txt file; it will iterate through every line and generate an image/video for each unique prompt.
• Prompt Folder: Point Amuse to a directory. It will scan for every text file and run a generation task based on the contents of each.
• Input Folder: The ultimate batch processor. Automatically run Upscale, Extract, Image or Video tasks on every image or video file found within a selected folder.

How to use

1. Navigate to the Automation tab (or the Automation section in your generation settings).
2. Select your Automation Type from the dropdown.
   • Tip: Hover over the mode to see a detailed tooltip of what it does!
3. Select your source file or folder.
4. Click Automate and let Amuse handle the queue.

Automations.mp4

Installation

This dev build is NOT compatible with previous versions of Amuse or existing ONNX models, full uninstall of Amuse 3.0 is REQUIRED.

Upgrade from v3.3.2 is supported

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

• New Install & Upgrade:
  1. Download and run Amuse_vX.X.X.exe.
  2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
2. Run Amuse.exe.

Upgrade:

1. Download and extract Amuse_vX.X.X.zip to a temp folder.
2. Copy and overwrite all files in your existing location
3. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.

---

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

• NVIDIA: Supports all CUDA compatible devices (CUDA 12.8).
• AMD: Supports Radeon 7000 series GPUs only (ROCm 7.2.1).
• Intel: Not Supported.
• Legacy Hardware: If you are using an incompatible device or older AMD hardware, it is highly recommended to stay on v3.2.0 until broader support is ported to the new engine.

---

Developers Note

Only install this version if you are interested in testing development builds. As I am a solo developer with very limited testing resources and only a few devices, things may not work, and features may be missing. Each dev build may require re-installs and other manual processes. Please only install if this is okay; otherwise, wait until a stable release is ready.

Full Changelog: v3.3.2...v3.3.3

v3.3.2 - New Inference Engine (pre-release)

Amuse v3.3.2 - New Inference Engine (pre-release)

This is a development build introducing a complete re-architecture of the inference engine. We are transitioning away from ONNX Runtime as the primary backend to a more modular engine supporting native Safetensors and GGUF.

This build serves as the first technical preview on the roadmap toward Amuse 4.0.

---

Technical Pivot: From ONNX to Native Weights

The legacy ONNX implementation required significant conversion overhead and lacked immediate compatibility with the latest research. The new engine changes this:

• Format Support: Added native loaders for .safetensors and .gguf.
• SOTA Integration: Provides the foundation to run FLUX.2, Z-Image, and LTX-2 without waiting for ONNX-specific optimizations or model conversions.
• Quantization: Automatic quantization to bfloat16, float8 or NF4 data types, support for GGUF allows for advanced bit-depth control (4-bit, 5-bit, 8-bit, etc.), significantly improving VRAM management for high-parameter models on consumer hardware.

---

What to Expect in this Dev Build

• New Backend Implementation: This is a ground-up rebuild. Expect instability as we port features over.
• Breaking Changes: Model loading logic has been overhauled. Existing ONNX models from your v3.0 install need to be updated to their Safetensors equivalents.
• Performance: Initial focus is on extensibility and compatibility. Performance tuning for specific AMD/NPU/GPU targets is ongoing.

---

Installation

This dev build is NOT compatible with previous versions of Amuse or existing ONNX models, full uninstall of Amuse 3.0 is REQUIRED.

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

• New Install & Upgrade:
  1. Download and run Amuse_vX.X.X.exe.
  2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
2. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.

---

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

• NVIDIA: Supports all CUDA compatible devices (CUDA 12.8).
• AMD: Supports Radeon 7000 series GPUs only (ROCm 7.2.1).
• Intel: Not Supported.
• Legacy Hardware: If you are using an incompatible device or older AMD hardware, it is highly recommended to stay on v3.2.0 until broader support is ported to the new engine.

---

Developers Note

Only install this version if you are interested in testing development builds. As I am a solo developer with very limited testing resources and only a few devices, things may not work, and features may be missing. Each dev build may require re-installs and other manual processes. Please only install if this is okay; otherwise, wait until a stable release is ready.

Full Changelog: v3.2.0...v3.3.2

v3.2.0 - .NET 10.0 + OnnxRuntime v1.23.0

Amuse v3.2.0

This release pushes Amuse into the next generation of performance by migrating the entire stack to .NET 10 and the latest OnnxRuntime.

Improvements

• Runtime Upgrade: .NET 10 We have moved the application to the .NET 10 framework. This transition brings the latest JIT optimizations and improved memory management, ensuring Amuse remains at the forefront of high-performance C# applications.

• Engine Update: OnnxRuntime v1.23.0 The core inference engine has been bumped to v1.23.0. This update provides broader support for the latest model architectures and improved execution providers for faster generation speeds.

• Dependency Modernization All internal NuGet libraries have been updated to their latest stable versions, ensuring better security, stability, and compatibility across the board.

---