TEST RECORDS · open-source AI models, run before written upISSUED MON & THU
EVERY MON & THU
Open-source AI models, tested to spec before you commit.
Setup notes, honest caveats and license checks for image, audio, vision and 3D models. Everything gets run before it gets written up. Two records every Monday and Thursday, free.
79 field reports on record · free
Latest field reports
Laguna-S-2.1FIELD NOTEISSUE #78FIELD NOTE
JUL 23, 2026
Work through coding tasks that span an entire codebase
Mage-FlowIMAGE · EDITISSUE #79IMAGE
JUL 23, 2026
Create images and edit them from plain written instructions
Qwen-Image-Edit-2509-Photo-to-AnimeIMAGE · GENERATIONISSUE #76MODEL
JUL 20, 2026
Turn any photo into an anime scene
Kimi-K2.7-CodeFIELD NOTEISSUE #77FIELD NOTE
JUL 20, 2026
Take a coding task from brief to working code
OvisOCR2FIELD NOTEISSUE #75FIELD NOTE
JUL 16, 2026
Turn any document page into clean Markdown, tables included
MOSS-Transcribe-DiarizeAUDIO · VOICEISSUE #74AUDIO
JUL 16, 2026
Transcribe long recordings with every speaker labeled
Gepard 1.0AUDIO · VOICEISSUE #72AUDIO
JUL 15, 2026
Generate live dialogue speech as the text streams in
Gemma 4 31BIMAGE · GENERATIONISSUE #73IMAGE
JUL 13, 2026
Ask one model about your images and entire documents
SCAIL-2VIDEO · MOTIONISSUE #70MODEL
JUL 9, 2026
Animate a character from one image using any driving video
SenseNova-Vision-7B-MoTVISION · PERCEPTIONISSUE #71MODEL
JUL 9, 2026
Run detection, depth, and segmentation from one vision model
FaceAnythingVISION · PERCEPTIONISSUE #68MODEL
JUL 6, 2026
Reconstruct and track a face across an image sequence
ViiTorVoiceAUDIO · VOICEISSUE #69MODEL
JUL 6, 2026
Clone and locally edit speech with emotion controls
12 of 79 records shownFULL ARCHIVE →