IV Image Viewer v2.1
Instant PSD, AI & EPS viewer with zero system bloat.
What it does
IV v2.1 is a native, ultra-lightweight Windows desktop viewer built under absolute resource constraints. It opens heavy PSD, AI, and EPS files instantly (<2s) with flatline memory recycling and a non-blocking asynchronous loop. 100% offline, secure, and free.
Does the same job
all alternatives →



- EAElectro – A hyper-fast Windows image viewer with a built-in terminal2025 · github.com · ▲46
This is my first major OSS release! I was always so frustrated by how slow image viewers were on Windows so I built one from the ground up with Rust & Tauri v2.0! Electro also has a very unique feature: a built-in terminal. I was always mesmerised by merging CLI tools with GUI based systems and this is my first go at it! I have big plans on expanding the terminal functionality with built-in image editing commands, command chaining, file handling etc.
- I4Ideogram 4.0 – open-weight 9.3B text-to-image modelJun 2026 · github.com · ▲46
It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
More work this month
the category →


The app store for voice native apps that lives in your notch
Work · 29d ago · voiceos.com


Mac-native app for screenshots, recordings and collaboration
Work · 5d ago · cleanshot.com
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai


- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com