The next RFDiffusion from Bakerlab (and Nvidia)
RFD4-Proteina

RFD4-Proteina designs proteins and biomolecular complexes with sequence–structure co-design, motif and binding-site conditioning, partial diffusion, and reward-guided search.

Key features:

Many design tasks from one model: monomers, protein and DNA binders, antibodies and nanobodies, enzymes and motif scaffolding, small-molecule pockets.
Rich conditioning: annotated CIF inputs or text-based YAML specifications (the quickest way to start) for fixed motifs, hotspots, burial, hydrogen bonds, and more.
Reward-guided search: beam search over generation paths scored by structure-prediction oracles and custom metrics.
Partial diffusion to refine or diversify existing structures.
Fast inference: torch.compile by default, with an optional BioIR backend (inference_backend=bioir).
Hugging Face release and Python API alongside the rfd4-generate, rfd4-evaluate and training CLIs.

I'm afraid we'll never see this work on our PCs :-(

---

Interesting video about RFD4

---