Nemotron Models Ideas Portal

1 Vote

AI-powered ComfyUI workflow optimizer that learns from 100K+ node graphs to automatically route compute across CPU/GPU, predict bottlenecks, suggest optimizations, and generate workflows from natural language—turning 2-hour manual pipeline construction into 30-second automated generation while maximizing RTX 4090 utilization.

Because it massive accelerates comfyui as a node set

Created 14 Oct 23:32

0
1 Vote

Al-powered USD translation engine in Omniverse that learns application-specific conventions (Houdini primitives + Maya meshes + Unreal actors • Blender objects) and automatically resolves schema conflicts, attribute mappings, and pipeline incompatibilities-enabling true interoperability across the VFX ecosystem.

No description provided

Created 14 Oct 23:21

0
1 Vote

Per-shot learning of quality thresholds that dynamically adjusts LOD transitions, Nanite cluster sizes, and impostor distances based on camera behavior and framerate targets.

No description provided

Created 14 Oct 23:04

0
1 Vote

Maintain full pipeline context across Houdini→USD→Unreal workflows to detect incompatibilities before export and auto-fix common translation issues.

No description provided

Created 14 Oct 23:03

0
1 Vote

Per-shot learning of quality thresholds that dynamically adjusts LOD transitions, Nanite cluster sizes, and impostor distances based on camera behavior and framerate targets.

No description provided

Created 14 Oct 23:02

0
1 Vote

Controlling reasoning length - define allowed number of tokens

To control the length of reasoning I want to be able to define the number of tokens the model can use in the final answer

Created 10 Sep 20:46

0
1 Vote

Hardware optimization - A model optimized for A10G GPUs

Develop a model that is most efficient on an A10G GPU

Created 10 Sep 13:40

0
1 Vote

Expanded Model Availability - Fireworks

No description provided

Created 10 Sep 13:27

0
1 Vote

Efficiency needs - I want to maximize throughput for large batches

Develop a model that excels in workloads with large batches, where the main goal is to optimize throughput

Created 10 Sep 13:24

0
0 Vote

Expanded Model Availability - Openrouter

No description provided

Created 10 Sep 13:23

0