NitroFusion2 debuts: a 1-2 step text-to-image model built on Z-Image-Turbo
bdsqlsz · x · 2026-11-06
NitroFusion2 is a new text-to-image model that generates images in just 1-2 steps, built on top of Z-Image-Turbo. Comparison grids show it beating TwinFlow, Z-Image-Turbo, Qwen-Image-2512 Turbo-2steps and Krea 2 Turbo-2steps on text rendering and fine detail — notably opera headdress details — at both 1-step and 2-step settings.
More from Multimodal
- Google ships Gemini Omni Flash 1.2 with 15-second video and 30% lower pricing — OfficialLoganK · 2026-11-06
- DRAMA expression-editing model launches free on Hugging Face for video and image editing — SimplyAnnisa · 2026-11-06
- Steampunk Warrior AI Art Wows With Intricate Gear and Brass Detail — azed_ai · 2026-11-06
- No filming, all AI: Seedance 2.5 + Suno workflow creates lifelike Italian music video — azed_ai · 2026-11-06
- GPT Image 2.5 creates Algiers tea-drinker character, animated with Seedance 2.5 — azed_ai · 2026-11-06
- NVIDIA launches Cosmos Framework and NIM to train, simulate and serve world models — NVIDIAAI · 2026-11-06