Image generation (experimental)

2026-01-19 · Source: Ollama Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning · Depth: Novice, quick

Summary

Ollama has introduced experimental image generation support on macOS, with Windows and Linux versions planned, allowing users to generate images via command-line prompts and preview them in compatible terminals. Key models include Alibaba's 6-billion parameter Z-Image Turbo, known for photorealistic output and bilingual English/Chinese text rendering under an Apache 2.0 license. Additionally, Black Forest Labs' FLUX.2 Klein, available in 4B (Apache 2.0) and 9B versions, offers fast image generation and strong readable text rendering, useful for UI mockups. Users can customize generation with parameters like image size, steps, random seed, and negative prompts, with images saving to the current directory.

Key takeaway

Ollama now offers experimental local image generation on macOS (soon Windows/Linux) with models like Alibaba's 6B Z-Image Turbo and Black Forest Labs' FLUX.2 Klein (4B/9B). Z-Image Turbo excels at photorealistic and bilingual text rendering (Apache 2.0), while FLUX.2 Klein focuses on readable text for UI/design. This provides accessible, configurable, and commercially viable local image synthesis for diverse applications directly from the terminal.

Topics

• Image Generation
• Ollama
• Z-Image Turbo
• FLUX.2 Klein
• Text-to-Image Models

Best for: AI Engineer, Machine Learning Engineer, Prompt Engineer

Related on AIssential

• RIP NANO BANANA! MOST VERSATILE NSFW COMPETITOR RIGHT NOW! — Flux 2 Klein is a versatile, fast, and low-VRAM AI model for comprehensive image generation and editing.
• Z-IMAGE TURBO UPGRADE! MORE DETAILS & CONTROLNET ON LOW VRAM! — New Z-image Turbo workflow enhancements improve image diversity, control, and detail, addressing prior model limitations.
• ChatGPT Images 2.0 Is Actually Crazy — GPT Image 2 demonstrates advanced image generation with functional barcodes and coherent text.
• Now in Foundry: Tongyi-MAI Z-Image-Turbo, with FLUX.1-schnell and SDXL base 1.0 — Microsoft Foundry now offers three advanced image generation models for diverse commercial and technical applications.
• Ollama is now available as an official Docker image — Ollama's official Docker image simplifies local LLM deployment with GPU acceleration on Linux.
• Build with Nano Banana 2, our best image generation and editing model — Nano Banana 2 enhances image generation with improved world knowledge, text rendering, and creative control for scalable visual applications.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Ollama Blog.