Bonsai ImagePrismML
|
Stable DiffusionStability AI
|
|||||
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
Stable Diffusion is Stability AI’s professional image generation model family built for creating high-quality visuals from text prompts. The models support a wide range of styles, including photography, 3D, painting, illustration, line art, and other creative formats. Stable Diffusion is designed for strong prompt adherence, diverse visual outputs, and flexible use across professional, creative, and technical workflows. Users can deploy the models through self-hosted licensing, the Stability AI API, cloud partner ecosystems, or web-based creative applications. Stability AI also provides image editing tools for inpainting, outpainting, object removal, upscaling, sketch control, structure control, and style transformation. Built for creators, developers, brands, and enterprises, Stable Diffusion helps teams generate, edit, customize, and scale visual content production.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Apple Silicon developers building private local image-generation apps that need compact diffusion models
|
Audience
Stable Diffusion is best suited for creators, designers, developers, marketers, brands, agencies, product teams, AI application builders, and enterprises that need flexible image generation, image editing, API access, self-hosted deployment, upscaling, style control, and scalable visual content creation
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
$0.2 per image
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationPrismML
Founded: 2026
United States
prismml.com
|
Company InformationStability AI
Founded: 2019
United Kingdom
stability.ai/stable-image
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Akuma
Blender
BlueGPT
DiffusionBee
Fuser
Hyperbolic
Jottingly AI
LastMile AI
Leo
Lewis
|
Integrations
Akuma
Blender
BlueGPT
DiffusionBee
Fuser
Hyperbolic
Jottingly AI
LastMile AI
Leo
Lewis
|
|||||
|
|
|