cd /news/artificial-intelligence/nitro-p-pixel-space-text-to-image-vi… · home › topics › artificial-intelligence › article
[ARTICLE · art-173343] src=rocm.blogs.amd.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Nitro-P: Pixel-Space Text-to-Image via Hierarchical Semantic-to-Pixel Generation

Nitro-P, an end-to-end pixel-space text-to-image diffusion framework built on the previously released Nitro-E, achieves 10.26 samples/s on a single AMD Instinct MI300X GPU for 512px image generation at batch size 32, with its distilled one-step variant reaching 90.02 samples/s. Nitro-P uses a hierarchical semantic-to-pixel design combining a patch-level semantic modeling component based on E-MMDiT with a pixel-level modulation-guided reconstruction component implemented as a lightweight U-Net decoder, removing the VAE decoder from the inference pipeline. The VAE-free design matters most in few-step sampling, where latent-space models still incur a non-negligible final decoding pass.

recommendation

For few-step text-to-image sampling, remove the VAE decoder and generate in pixel space with a hierarchical semantic-to-pixel design; Nitro-P measured 10.26 samples/s at 512px on one MI300X, rising to 90.02 with one-step distillation.

more in playbook: Inference and self-hosting
by read1 min views1 publishedNov 20, 2026

We present Nitro-P, an end-to-end pixel-space text-to-image (T2I) diffusion framework. Built upon our previously released Nitro-E, Nitro-P extends the Nitro family from latent-space T2I generation to a VAE-free pixel-space design. To achieve both high generation quality and computational efficiency, Nitro-P adopts a hierarchical semantic-to-pixel design, consisting of a patch-level semantic modeling component based on E-MMDiT and a pixel-level modulation-guided reconstruction component implemented as a lightweight U-Net [1] decoder. By operating directly in pixel space, Nitro-P removes the VAE decoder from the inference pipeline. This benefit is most visible in few-step sampling, where latent-space models still incur a non-negligible final decoding pass. Nitro-P achieves a throughput of 10.26 samples/s on a single AMD Instinct™ MI300X GPU for 512px image generation with a batch size of 32. Its distilled one-step variant further boosts throughput to 90.02 samples/s.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @nitro-p 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/nitro-p-pixel-space-…] indexed:0 read:1min 2026-11-20 · —