DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to generate SDXL and ComfyUI images faster on RTX cards with GPU Unlock

Remove the FP16 tensor cap so diffusion models in ComfyUI render faster.

Short answer: Install GPU Unlock and set gpu_unlock.targets=all on the kernel command line; then Reboot and open ComfyUI as usual; Render the same seed and workflow you used before and compare the time per image. All steps.

system-change. Kernel module installed at boot; not supported by NVIDIA.

Who it is forAn artist or tinkerer running SDXL, SD 1.5 or DiT models in ComfyUI on a GeForce card.

The problemEach image takes longer than it should because FP16 tensor math is held at half rate.

The outcomeThe README reports 30 to 55 percent faster FP16 or BF16 image generation, with identical outputs.

What you need first

  • Linux (Windows is not supported; the README points to a third party port)
  • An Ampere RTX 30 card (stable) or an Ada RTX 40 or Turing RTX 20 card (experimental); RTX 50 is not supported
  • Root access to install a kernel module and edit the kernel command line

Steps

  1. Install GPU Unlock and set gpu_unlock.targets=all on the kernel command line
  2. Reboot and open ComfyUI as usual
  3. Render the same seed and workflow you used before and compare the time per image
  4. Note quantized INT8, FP8 and INT4 models and gaming see no change

Prompt for your agent

Help me install Zagitta/gpu-unlock and measure ComfyUI SDXL render time on my <card> before and after with the same seed and workflow.

Caveat. This card is written from the Zagitta/gpu-unlock README, not from a test run by Deduped. Before you start, make sure you have Linux. Check the repo for newer instructions before you rely on these steps.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Zagitta/gpu-unlock and "Generate SDXL and ComfyUI images faster on RTX cards"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer