Bonsai ImagePrismML
|
FLUX 3 ImageBlack Forest Labs
|
|||||
Related Products
|
||||||
About
Bonsai Image Ternary 4B MLX 2-bit is a ternary-weight text-to-image diffusion transformer deployment for Apple Silicon. It is built as a quality-oriented Bonsai Image variant, using ternary {−1, 0, +1} transformer weights with FP16 group-wise scaling in the matrix-heavy transformer layers, including Q/K/V projections, output projections, and MLP weights. The model reduces the FLUX.2 Klein 4B transformer from 7.75 GB FP16 to a 1.21 GB Bonsai Image transformer, a 6.4× smaller footprint, while keeping visual quality and prompt fidelity close to the original model. The Apple Silicon deployment payload is 3.88 GB, including the MLX 2-bit diffusion transformer, a 4-bit Qwen3-4B text encoder, and an FP16 Flux2 VAE. After prompt encoding, the text encoder is offloaded, so the denoising loop only keeps the compact transformer and VAE resident. The model uses a 4-step FlowMatchEuler sampler with guidance 1.0 and shift 3.0, with no CFG and no negative prompts required.
|
About
FLUX 3 Image is an AI image generation and editing model from Black Forest Labs designed to provide precise control over image composition and individual visual elements. It supports text-to-image generation with prompt following and lets users position elements using bounding boxes on a coordinate-based canvas. Users can perform multiple targeted edits while keeping specified parts of the original image unchanged. The model can also combine as many as 10 reference images into a single composed image, allowing specific objects, clothing, styles, and other visual references to be incorporated into a new result. FLUX 3 Image supports native 2K and 4K rendering to preserve details such as textures, faces, and colors, along with pixel-level editing of selected image regions. The model is also designed for use by AI agents and is available under a commercial weights license for organizations that want to fine-tune and deploy image generation on their own infrastructure.
|
|||||
Platforms Supported
Windows
Supported
Mac
Supported
Linux
Supported
Cloud
Not Supported
On-Premises
Supported
iPhone
Supported
iPad
Supported
Android
Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Apple Silicon developers building private local image-generation apps that need compact diffusion models
|
Audience
Designers, creative professionals, developers, AI application builders, marketing and media teams, visual content creators, enterprises, and agent developers that need controllable image generation, high-resolution rendering, reference-based composition, or precise AI image editing
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Supported
|
|||||
Screenshots and Videos |
Screenshots and VideosNo images available
|
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationPrismML
Founded: 2026
United States
prismml.com
|
Company InformationBlack Forest Labs
Founded: 2024
Germany
bfl.ai/models/flux-3-image
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Collart AI
Not Supported
FLUX 3
Not Supported
FLUX Upscale
Not Supported
|
||||||
|
|
|