Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer — mentioned by user34283

Sat, 17 Jan 2026 09:59:28 GMT

The team behind Z-Image Turbo has told us multiple times in their paper that the output quality of the Turbo model is superior to the larger base model. I think that information still did not get through to most users. "Notably, the resulting distilled model not only matches the original multi-step teacher but even surpasses it in terms of photorealism and visual impact." "It achieves 8-step inference that is not only indistinguishable from the 100-step teacher but frequently surpasses it in perceived quality and aesthetic appeal" https://arxiv.org/abs/2511.22699

Paper and discussion history. A mention is not an endorsement.

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer — HN submission

Tue, 02 Dec 2025 03:26:26 GMT

Z-Image: An Efficient Image Generation Foundation Model [pdf]

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer · HackerPapers discussions

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer — mentioned by user34283

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer — HN submission