A focused feed of models, agents, research and open-source releases for people building with AI.
Pruna AI open-sourced P-H3-Image , converting MiniMax-H3 video model into an image generator. Generates 8-megapixel images in 8 steps, roughly 5x faster than the base model. Smallest w4a8 variant is a 20 GB download peaking at 21 GB VRAM, versus 143 GB for MiniMax-H3.
New paradigm, Anthropogenic Regional Adaptation , measures human-centric regional alignment in vision-language models. GG-EZ method combines regional data filtering, supervised fine-tuning, and weight merging to localize models cheaply.
Mesh Avatar Studio turns one illustration into an animated 2D VTuber rig, hitting ~1.8k GitHub stars under MIT license . A coding agent (Claude Code or Codex) places the mesh, cuts layers and reviews poses from docs/agent-guide.md .
Community quant repack of Qwen-Image-2.1-Turbo hits 2.5M downloads and 4.5k likes on Hugging Face. Eleven formats: GGUF (Q4 to Q8), FP8, INT8 ConvRot, NVFP4 safetensors, and MLX 4/6/8-bit for Apple Silicon. Base model generates in 8 denoising steps at CFG 1, versus 40 steps for Qwen-Image-2.1.
Google released MedGemma , open medical vision-language models built on Gemma 3 4B and 27B. Includes MedSigLIP , a 400M medical vision encoder usable standalone for classification and retrieval. Scores 86.2% on MedQA, best open model at release aside from DeepSeek-R1.
Krea 3 Ultra debuts at #4 on Arena, Artificial Analysis, and Design Arena editing leaderboards . Finishes edits in ~8s, 3-5x faster than Nano Banana Pro and 11x faster than GPT Image 2.5. $80 per 1k edits vs $150 for Nano Banana Pro and $436 for GPT Image 2.5.
Topaz Labs released Wonder 4 , a one-click upscale, denoise, and sharpen model. First Topaz model built on a mixture-of-experts architecture that routes enhancements per image region. Combines upscaling, denoising, deblurring, compression artifact removal, and face recovery in a single pass.
MER-Bench introduces Meme Reappraisal: flipping a meme's emotion while keeping scene, characters, and layout intact. Task inspired by cognitive reappraisal in psychology, framed as constrained multimodal generation.
Bergen team introduces GsCNN, an SO(3)-equivariant architecture for scalar and vector fields on the sphere ( paper ). Removes kernel and nonlinearity constraints that limited previous spherical CNNs. Each layer: SO(3) conv, inverse FT, nonlinearity, FT, smoothing in output spin.
EQ-VMamba is the first rotation-equivariant visual Mamba, guaranteeing consistent outputs under 90-degree rotations. Core innovations: EQ-cross-scan with four symmetric paths and group Mamba blocks sharing weights across orientations.
Comfy-Org released a ComfyUI-ready repackage of Speridlabs' Idol image-to-3D model. Idol turns one image into a 3D Gaussian splat with up to 1,048,576 Gaussians. Runs on consumer GPUs in under 7.2 GB of VRAM, generates 1M splats in roughly 3 seconds on high-end hardware.
OpenGVLab released InternVL2-1B , a 0.9B parameter vision language model under MIT license. Combines InternViT-300M-448px vision encoder with Qwen2-0.5B-Instruct language backbone via MLP projector. Scores 754 on OCRBench, beating larger PaliGemma-3B (614) and Mini-InternVL-2B (654).
Unsloth released GGUF quants of Qwen-Image-2.1-Turbo, the 8-step distilled version of Qwen's 7B image model Sizes range from 2.47 GB (Q2_K) to 14.23 GB (F16); Q4_K_M at 4.2 GB is the recommended rung Uses Unsloth Dynamic 2.0, which keeps critical layers at higher precision for better accuracy at
Sperid Labs released Idol , an Apache 2.0 image-to-3D Gaussian splat model. 600M parameter 3D-DiT runs on consumer GPUs using 7.2 GB VRAM, outputs standard .ply files. Generates up to 1,048,576 Gaussians per object, 3.4 s on B300, 6.7 s on H100.
Agent Sprite Forge 0.4 turns one approved master still into a full six-action sprite set. Pipeline: master still, image-to-video per action, soft-matte key, loop detection, retime, finish, package. Supports OpenAI, Gemini, xAI, BytePlus, fal.ai APIs with Codex/Grok CLI fallback.
Krea Nodes now supports real-time multiplayer editing on its node-based workflow canvas . Multiple teammates can edit, run nodes, and view outputs in the same project simultaneously. Live cursors and shared runs let roles split: one wires prompts, another swaps images, another queues jobs.
Microsoft released Mage-VL-Cowork , a 4B hybrid computer-use agent under Apache-2.0. Scores 66.0% on OSWorld-Verified, best among 4B models, versus 72.4% human reference. Dynamically switches between GUI clicks ( computer_use ) and shell commands ( bash ) per turn.
Cagliostro Lab released Animagine XL 4.0 , a full SDXL retrain for anime generation. Trained on 8.4M images for ~2650 GPU hours on 7x H100 80GB. Opt variant improves anatomy, color saturation, noise, and output stability.
Speridlabs released Idol , a single-image to 3D Gaussian splat model under Apache 2.0. Up to 1,048,576 Gaussians per object, 7.2 GB VRAM peak, under 2 seconds on datacenter GPUs. Diffusion transformer (370M DiT) with DINOv3 and FLUX.2 VAE image conditioning, BiRefNet background removal.
Google AI Studio now supports XR Blocks for prompt-to-app extended reality development Single prompt generates apps with hand tracking, pinch gestures, and tabletop or wall physics Can generate 360 degree 3D holograms directly from text or photos Powered by Gemini plus the open-source XR Blocks
Krea launched Ad Studio : paste a URL, get a brand kit plus dozens of on-brand ads Powered by a new Krea 3 expert model fine-tuned specifically for advertising creative Krea 3 does 2K edits in under 8 seconds at $0.06 per image, roughly a third of competitor pricing First editing model with LoRA
NVIDIA's LucidLyra turns one image into a 3D Gaussian scene with geometry, semantics, and instances. A frozen camera-controlled video diffusion model supplies multi-view latents to a single Gaussian decoder.
Liquid AI launched LFM3, a tri-hybrid family of six open-weight 2B models spanning text, vision, audio, omni, and decision tasks, all fine-tunable on a single GPU.
PhysAg3D generates physically interactive 3D assets from a single image, with joints and soft bodies ready for simulation Pairs a frozen image-to-3D mesh generator with a vision-language agent that reasons about parts and interactions Hierarchical representation links interaction intent to joints
No stories match these filters.
