AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: Image Generation
36 article(s) found · Clear tag
Pixal3D – Tencent & Tsinghua Open Single-Image 3D Generation
Pixal3D is a single-image 3D generation project from Tencent ARC Lab, Tsinghua University, and Victoria University of Wellington. Via a back-projection mechanism, it lifts 2D pixel features explicitly...
ELF – The First Diffusion Language Model from Kaiming He's Team
ELF (Embedded Language Flows) is the first continuous-diffusion language model from Kaiming He's team, overturning the logic of autoregressive text generation. It denoises entirely in continuous embed...
HiDream-O1-Image – HiDream.ai's Open-Source Native Unified Image Generation Model
HiDream-O1-Image is an 8B-parameter pixel-native unified image generation model from HiDream.ai (智象未来), built on the world's first UiT (Unified Transformer) architecture. It abandons the classic diffu...
Gemini Omni Flash – Google's Multimodal Video Generation Model
Gemini Omni Flash is Google's unified multimodal world generation model unveiled at I/O, positioned to break traditional generative model modality barriers and enable any-input to any-output full-pipe...
HiDream-O1-Image-Pro – HiDream.ai's Flagship Image Model
HiDream-O1-Image-Pro is HiDream.ai's flagship image generation model built on the native full-modal UiT (Unified Transformer) architecture with over 200B parameters. It sets new SOTA across text-to-im...
Rodin Gen-2.5 – Hyper3D's 10M-Polygon AI 3D Model Generator
Rodin Gen-2.5 from Hyper3D (影眸科技) is marketed as the first commercial AI 3D tool to generate 10M+ polygons directly, built on SIGGRAPH 2025 Best Paper technology. Text, single-image, or multi-view inp...
Qwen-Image-Bench – Qwen Team's Text-to-Image Model Evaluation Benchmark
Qwen-Image-Bench is a standardized benchmark dataset from Alibaba's Qwen team (Tongyi Qianwen) for evaluating text-to-image models—1,000 carefully designed test samples covering Chinese and English pr...
MAI-Image-2.5 – Microsoft's Flagship Text-to-Image Model
MAI-Image-2.5 is a flagship text-to-image model from Microsoft Research and the strongest release in the MAI-Image family. On the Arena text-to-image leaderboard it climbed to #3 with 1,254 points—72 ...
Image-to-LoRA-V2 – ModelScope's Training-Free Style Transfer Tool
Image-to-LoRA-V2 (i2L-V2) is a training-free style transfer tool open-sourced by ModelScope's DiffSynth-Studio team. Upload 1–8 style-consistent reference images and the model predicts text-to-image L...
Ideogram 4 – Ideogram's Open-Source Text-to-Image Model for Design
Ideogram 4 is Ideogram's first open text-to-image model—9.3B parameters, trained from scratch rather than fine-tuned from an existing checkpoint. Built for high-quality design, marketing graphics, log...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.