ARCHIVE · every field report on record
Archive

Every field report

Each record is a model we actually set up and ran, with the setup notes and caveats intact. Browse by category or search by model name.

JULY 2026

#78Work through coding tasks that span an entire codebaseLaguna-S-2.1#79Create images and edit them from plain written instructionsMage-Flow#76Turn any photo into an anime sceneQwen-Image-Edit-2509-Photo-to-Anime#77Take a coding task from brief to working codeKimi-K2.7-Code#75Turn any document page into clean Markdown, tables includedOvisOCR2#74Transcribe long recordings with every speaker labeledMOSS-Transcribe-Diarize#72Generate live dialogue speech as the text streams inGepard 1.0#73Ask one model about your images and entire documentsGemma 4 31B#70Animate a character from one image using any driving videoSCAIL-2#71Run detection, depth, and segmentation from one vision modelSenseNova-Vision-7B-MoT#68Reconstruct and track a face across an image sequenceFaceAnything#69Clone and locally edit speech with emotion controlsViiTorVoice#66Run an open coding assistant for tool-based agent workOrnith-1.0-9B#67Parse long documents and PDFs with open OCRUnlimited-OCR

JUNE 2026

#65Re-pose a subject from a reference image and depth mapRefControl FLUX.2 Klein Depth#64Remove or refill parts of an image with a small open modelMoebius#63Generate creative image concepts and train custom stylesKrea-2-Turbo#62Apply a reference style while preserving the source imageTeleStyleV2#61Turn images into structured JSON with custom fieldsLFM2.5-VL-1.6B-Extract#60Edit photos with prompt instructions and generate fast imagesBoogu Image#58Transcribe live multilingual speech with latency controlnemotron-3.5-asr-streaming-0.6b#59Swap a face or full head while preserving the sceneBFS-Best-Face-Swap#56Generate multiple webpage drafts from one promptRWKV Gradio 3#57Parse scanned documents into text, tables, formulas, and chartsPaddleOCR-VL-1.6#55Generate expressive speech with voice cloning controlsHiggs Audio v3 TTS#54Generate design-ready images with readable text and layout controlIdeogram 4#52Use a reference photos to make targeted image edits quicklyPro Realism Edit Studio#53Convert a single image into a controllable 3D splatTripoSplat#51Find moments in videos with natural languageMarlin-2B#50Find Objects in Images and Videos with Natural LanguageLocateAnything-3B

MAY 2026

#49Edit Uploaded Images at Higher ResolutionFireRed Image Edit 2K#48Compare native and 4x upscaled generationsnvidia/pid#47Generate and edit long-form music and sound effectsStable Audio 3#46Generate 1K images directly in pixel spaceL2P#44Generate images closer to the pixels for cleaner detailAsymFLUX.2-klein#45Extract text, tables, and formulas from document imagesGLM OCR#42Add or remove objects in a photo without redoing the sceneQwen Image Edit Object Manipulator#43Direct speech like a scene, with pauses, laughs, and whispersDramaBox#41Restore compressed cartoon frames at 2xStarsample V2.0#40Turn one object photo into an exportable textured meshPixal3D#38Generate, edit, and reuse a subject across scenesHiDream-O1-Image#39Generate and edit images in one flowSenseNova-U1#37Generate poster-style images with readable text, fastERNIE-Image-Turbo#36Turn any photo into a toy-style action figureSYSTMS ACTION#34Turn road-object photos into simulation-ready 3D assetsAsset Harvester#35Speak 30 languages with a voice you design or cloneVoxCPM2

APRIL 2026

#32Redact names, emails, and secrets before text leaves your machineOpenAI Privacy Filter#33Label 28 body parts in any photo of a personSapiens2 Seg#30Reason over a million tokens of code and documentsDeepSeek-V4-Pro#31Generate images with a big model that only uses what it needsNucleus-Image#28Expand a video to a new aspect ratio without croppingLTX 2.3 Outpaint#29Ask questions about long audio, speech, and musicAudio Flamingo Next#26Turn a plain-English song idea into a finished trackace-step-jam#27Reconstruct a 3D world from photos or a short videoHY-World 2.0#25Turn dense PDFs into structured Markdown and JSONMinerU OCR#24Extract text and layout from documents and screenshotsNemotron OCR v2#22Repair text, logos, and small defects in one region of an imageRefineAnything#23Generate editable 3D motion from text and constraintsKimodo#21Split an anime illustration into editable PSD layersSee-through#20Rebuild a 3D scene from a photo set or short videoSAIL-Recon#18Remove an object from video and fix what it touchedVOID#19Clone a voice or design one from a descriptionOmniVoice#17Transcribe speech in 14 languages, in the browser or locallyCohere Transcribe#16Animate a still image with one motion promptWan2.2 14B Fast Preview

MARCH 2026

#14Turn charts and figures into editable SVGVFig#15Animate a portrait using a motion clip, lip sync includedLTX 2.3 Sync#12Generate conversational speech that sounds like a real exchangeCSM-1B#13Generate video with matching audio from one promptLTX-2.3#11Clone a voice from a short clip without a heavy setupLuxTTS#10Generate a textured 3D model from one imageHunyuan3D-2.1#8Turn any image into a dense, usable captionJoy Caption Alpha Two#9Edit images fast without rebuilding the whole frameFLUX.2-klein-9b-kv#6Find and track anything in a video by naming itQwen3-VL Video Grounding#7Cut a subject cleanly out of any photoBackground Removal#5Change the camera angle of an image without rebuilding the sceneQwen-Image-Edit-2511-Multiple-Angles-LoRA#4OmniLottie: Lottie Animation from Text, Images, or VideoOmniLottie#3Generate images with text that stays readableQwen-Image-2512#2Chatterbox: Open Multilingual TTSChatterbox#1Talk to a model that sees, listens, and answers in real timeMinicpm O 4.5
79 records shown↑ BACK TO TOP