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
The P-Image-Ideogram represents a collection of Pareto-optimal text-to-image models, expertly crafted by Ideogram in collaboration with Pruna AI, aiming to strike an exceptional balance between image quality, generation speed, and overall efficiency. These models are specifically engineered for high-volume production and quick iterations, enabling the creation of 1,000 images in mere seconds while still delivering quality that rivals top-tier image models. Users have the flexibility to choose from four Quality levels, allowing them to align computational resources with their specific requirements rather than adhering to a simplistic hierarchy of quality. The Medium setting acts as the standard default, while High is tailored for intricate typography, elaborate prompts, and detailed nuances; very Low or Low settings are ideal for drafts, experimentation, and extensive A/B testing. Developers can seamlessly interact with the model via a synchronous API endpoint, where they can submit either a natural-language request or a structured Ideogram 4.0 JSON prompt, with the server automatically recognizing the format. In addition, optional prompt upsampling enhances instructions through the Magic Prompt feature, and a fixed seed guarantees that results can be replicated consistently, making this model not only versatile but also reliable for varied applications. Overall, the P-Image-Ideogram stands out as a powerful tool for creators seeking efficiency and quality in their text-to-image tasks.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
JSON
No
Model Context Protocol (MCP)
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
Ideogram
Founded
2022
Country
Canada
Website
ideogram.ai/tools/p-image-ideogram