Bonsai ImagePrismML
|
Qwen-Image-2.1Alibaba
|
|||||
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
Qwen-Image-2.1 is a unified text-to-image generation and image editing model in the Qwen family, designed to balance generation quality, inference efficiency, and versatility. Its visual generation component contains 7B parameters and uses 32 Single-Stream DiT layers, with a lightweight architecture that combines mixed-granularity attention and prefix KV cache reuse to deliver strong image quality at lower computational cost. The model natively supports both regular and transparent RGBA image generation, transparent-layer editing, and subject extraction from photographs within a single system. For image editing, it can use up to 10 reference images for multi-subject composition, accept local edit instructions through circles, painted annotations, or separate masks, and preserve the identity of people and products. Improvements to typography, portrait lighting, realistic textures, and fine details are designed to produce more refined and visually compelling results.
|
|||||
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
Developers, researchers, and creative AI teams seeking to generate, edit, compose, and manipulate high-quality images with an open source multimodal generation model
|
|||||
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
No information available.
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 InformationAlibaba
Founded: 1999
China
github.com/QwenLM/Qwen-Image-2.1
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Happy Shrimp 1.0
Qwen
Qwen Studio
QwenCloud
|
||||||
|
|
|