Bonsai ImagePrismML
|
P-Image-IdeogramIdeogram
|
|||||
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
P-Image-Ideogram is a family of Pareto-optimal text-to-image models built by Ideogram with Pruna AI to deliver a strong balance of image quality, generation speed, and efficiency. Designed for high-volume production and rapid iteration, it produces 1K images in seconds while maintaining quality near leading image models. Four Quality levels let users match compute to the brief rather than follow a simple worse-to-better ladder. Medium serves as the everyday default, High is suited to dense typography, complex prompts, and fine details, and Very Low or Low support drafts, testing, and broad A/B exploration. Developers can access the model through a synchronous API endpoint and submit either a natural-language prompt or a structured Ideogram 4.0 JSON prompt, which the server detects automatically. Optional prompt upsampling can expand instructions through Magic Prompt, while a fixed seed supports reproducible 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
Creative automation teams that need to generate large volumes of polished campaign visuals and design variations quickly
|
|||||
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 InformationIdeogram
Founded: 2022
Canada
ideogram.ai/tools/p-image-ideogram
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
JSON
Model Context Protocol (MCP)
|
||||||
|
|
|