Arx Cruz·22h agoI Ran an Open-Source AI Video Character Swap on an M5 Pro Mac and an RTX 5080.Open-source video models are moving fast enough that “can I run this at home?” is now a fair question. So I picked a demanding one…
Namsii Z·1d agoGPU Cloud with a Preconfigured ComfyUI Image: Build a Session You Can ReopenA GPU cloud with a preconfigured ComfyUI image is most useful when it gets you to a working graph and lets you explain how to run that…
Sergio Perez Rodriguez·1d agoBuilding a Synthetic Media Engine, Pt1: Identity Preserved Image GenerationAbout
Vivastory Lab·2d agoFixing AI Manga Faces with ComfyUI FaceDetailer: Not SolvedI’m Labo, the lighthouse keeper. Today’s page is about AI manga faces: I tried to fix them with ComfyUI FaceDetailer, and it still isn’t…
Vivastory Lab·3d agoWhy Is My AI Coloring Flat? Shaded Sketches vs Line ArtI’m Labo, the lighthouse keeper. Today’s page is the time my AI coloring came out flat: I gave the AI a sketch with the shadows already…
Vivastory Lab·3d agoSketch to AI Manga: Does ControlNet Scribble Keep Lines?I’m Labo, the lighthouse keeper. Today’s page is about how to turn your own sketch into manga with AI: putting a sketch into ControlNet…
InDiffusion DoodlesbyChris Green·4d agoSmall Model Overload: Krea 2, Qwen Image 2.1 & MOSS ImageDo I need them all?
Mo moufakkir·6d ago8 Open-Source Alternatives to Higgsfield Worth ExploringFrom character swaps and creative canvases to camera planning and video editing, these projects bring AI production tools into open…
Vivastory Lab·Nov 3LoRA Trained for 56 Minutes, No Style: The AI Never LookedI’m Labo, the lighthouse keeper. My first LoRA training ran for 56 minutes and the style still didn’t come out, and today I show the…
