This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
SilkStack Image Browser
Beautiful local ComfyUI catalog with on-device WebGPU search
SilkStack is a cross-platform desktop viewer built for ComfyUI creators and local AI art collectors. It runs custom-compiled qwen3-embedded models natively on your GPU via WebGPU and WebLLM, enabling multi-lingual semantic search, local LLM auto-tagging, and deep PNG/JSON workflow inspection—100% offline with zero external API dependencies.
Hey Product Hunt community! 👋
I’m the maker of SilkStack Image Browser. Over the last 6 months, I’ve been heavily experimenting with local AI workflows using ComfyUI. As my output folders grew into thousands of images, I realized standard file explorers and traditional keyword search just weren’t cutting it.
I initially started by forking Image-MetaHub, but turned it into my main playground for embedding local AI natively into desktop applications—with zero server overhead, no API subscriptions, and full offline privacy.
🌟 Why I Built SilkStack:
Effortless Organization & Quality Proofing: Fast cataloging, side-by-side inspection, and sorting to ensure you quickly identify and select your highest-quality image generations. It handles classification and filtering based on deep PNG/JSON metadata parsing.
True Semantic Search: Searching by raw prompt keywords often fails if you forgot the exact words used months ago. With SilkStack, you can search by intent, mood, or context (e.g., typing "rainy cyberpunk neon aesthetic" brings up matching renders, even if those words aren't in the PNG info).
On-Device WebGPU Inference: Finding efficient embedding models for WebLLM was tough, so I compiled a custom version of qwen3-embedded specifically for this app. It executes on your GPU via WebGPU locally on your machine.
Auto-Tagging & Classification: Automatically generate image tags and categories via an embedded local LLM pipeline.
ComfyUI Graph & Metadata Inspector: Native, high-density gallery view built specifically to parse complex node workflows instantly.
🛠️ Tech Stack:
Electron, React, TypeScript, WebGPU, WebLLM, and an embedded local vector database. (The compiled embedding model is also open-sourced on Hugging Face at huggingface.co/skkut for anyone building WebGPU apps!)
💡 Pricing Model:
Core image browsing, prompt extraction, workflow inspection, and standard organization tools are 100% free. Advanced on-device AI capabilities (like local semantic search and auto-tagging) are unlocked via a small, one-time lifetime license.
Would love to hear your feedback, workflow suggestions, or answer any questions about running WebGPU models locally on desktop! 🚀
About SilkStack Image Browser on Product Hunt
“Beautiful local ComfyUI catalog with on-device WebGPU search”
SilkStack Image Browser was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #148 on the daily leaderboard. SilkStack is a cross-platform desktop viewer built for ComfyUI creators and local AI art collectors. It runs custom-compiled qwen3-embedded models natively on your GPU via WebGPU and WebLLM, enabling multi-lingual semantic search, local LLM auto-tagging, and deep PNG/JSON workflow inspection—100% offline with zero external API dependencies.
On the analytics side, SilkStack Image Browser competes within Artificial Intelligence, GitHub, Digital Art and Design resources — topics that collectively have 527.9k followers on Product Hunt. The dashboard above tracks how SilkStack Image Browser performed against the three products that launched closest to it on the same day.
Who hunted SilkStack Image Browser?
SilkStack Image Browser was hunted by Saravana Karthikeyan. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of SilkStack Image Browser including community comment highlights and product details, visit the product overview.
Saravana Karthikeyan