groundboxerrespect/Dlls5-auto

🎮 Self-hosted neural rendering & AI image enhancement service inspired by DLSS 5. Turn any photo, screenshot or game capture into a photoreal cinematic render — bloom, filmic tone mapping, 6 style presets, REST API, batch mode. Python + FastAPI + Docker. Free & open-source.

What it solves

It provides a self-hosted way to apply a "neural rendering" aesthetic to images, screenshots, and artwork. It aims to replicate the photorealistic lighting, cinematic bloom, and filmic tone mapping associated with high-end AI-driven graphics without requiring specific high-end hardware.

How it works

The service uses a multi-pass image processing pipeline that includes bloom diffusion, ACES-style tone mapping, local contrast adjustments, and adaptive sharpening. It is built as a FastAPI application that can be deployed via Docker or Python. While it has a built-in CPU-friendly engine based on NumPy and Pillow, it also includes a hook to swap the backend for a local Stable Diffusion or diffusion-based engine.

Who it’s for

Developers, gamers, and digital artists who want to enhance images with cinematic styles via a REST API or a web interface, and who prefer to keep their data on their own hardware.

Highlights

  • Style Presets: Includes pre-configured looks like Cinematic, Photoreal, Neon Night, and Golden Hour.
  • Flexible Deployment: Supports one-command Docker deployment and a simple Windows installer.
  • API-First: Offers a REST API for single image generation and batch processing of ZIP archives.
  • Hardware Agnostic: The built-in engine runs on any machine, including those without a GPU.

Related

  • Project
    gongnyang/gongnyang-prompt-kit

    A prompt compilation kit for Claude Code that transforms vague image requests into professional, validated prompts for gpt-image-2.

  • Project
    gazingstars123/Anima-Standalone-Trainer

    A lightweight training environment with a Web UI for performing LoRA fine-tuning on the Anima model.

  • Project
    lynote-ai/ai-image-detector

    AI Image Detector is an open‑source Python tool that estimates how likely an image was generated by AI. It ships with several ready‑made back‑ends (UnivFD, Sentry, Nonescape, hybrid ensembles) and lets you run a single command (`aidetect detect …`) on a file or folder, outputting a probability and label. Optional extras give a Gradio web UI or a FastAPI server. The repo includes benchmarking scripts, threshold‑calibration, and clear guidance on which backend to pick. It’s a lightweight, install‑once‑run‑anywhere utility for AI‑image detection, with documented limitations (no universal guarantee, no region‑level localization).

  • Project
    nregret/Comfyui-Anima-Tools

    A visual prompt and LoRA selection suite for ComfyUI designed for anime AI art, featuring databases of 40k+ artists, characters, and clothing tags.