Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
The Bonsai Image Ternary 4B MLX 2-bit is a text-to-image diffusion transformer specifically designed for deployment on Apple Silicon, emphasizing quality in its Bonsai Image variant. This model utilizes ternary weights of {−1, 0, +1} along with FP16 group-wise scaling in its transformer layers, which encompass Q/K/V projections, output projections, and MLP weights. Notably, it reduces the size of the FLUX.2 Klein 4B transformer from 7.75 GB FP16 to just 1.21 GB, achieving a remarkable 6.4× smaller footprint while maintaining visual quality and fidelity to prompts akin to the original model. The deployment package for Apple Silicon is 3.88 GB, which includes the MLX 2-bit diffusion transformer, a 4-bit Qwen3-4B text encoder, and an FP16 Flux2 VAE. After the text encoder handles prompt encoding, it is offloaded to ensure that only the compact transformer and VAE remain in memory during the denoising loop. Furthermore, the model employs a 4-step FlowMatchEuler sampler with guidance set at 1.0 and a shift of 3.0, eliminating the need for CFG and negative prompts, thus streamlining the generation process for enhanced user experience. Overall, this innovation represents a significant advancement in efficient and effective image generation technology.
Description
FLUX 3 Image is an AI image generation and editing model from Black Forest Labs built for detailed control over composition, image elements, and localized edits. Users can generate images from standard text prompts or define the placement of individual elements with bounding boxes. Bounding boxes operate on a 0-to-1000 coordinate grid regardless of the selected aspect ratio, providing a structured way to specify where subjects and objects should appear. For conventional text-to-image generation, the model provides prompt following and a native understanding of image composition without requiring users to manually create a layout. Its editing capabilities allow several elements to be modified within an image while other designated elements and the surrounding composition remain unchanged. FLUX 3 Image can use up to 10 reference images and combine their specified elements into a newly composed scene. Native 2K and 4K rendering is available for preserving fine details, textures, faces, and colors at high resolutions. Pixel-perfect editing enables users to change selected areas while preserving the rest of an existing image. The model is natively trained to understand image layout and composition, making it suitable for AI agents that need to plan and generate well-composed visuals from text instructions. Organizations operating image generation at scale can also license commercial model weights to fine-tune FLUX 3 Image and deploy it on their own infrastructure.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Collart AI
No
FLUX 3
No
FLUX Upscale
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
No
On-Premises
Yes
iPhone App
Yes
iPad App
Yes
Android App
Yes
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
PrismML
Founded
2026
Country
United States
Website
prismml.com
Vendor Details
Company Name
Black Forest Labs
Founded
2024
Country
Germany
Website
bfl.ai/models/flux-3-image
Product Features
Product Features
Alternatives
Alternatives
No Alternatives