AI Briefing#image-generation
The latest AI and developer news about #image-generation, with the original source and a short summary.
The latest AI and developer news about #image-generation, with the original source and a short summary.
The framework scales group size quadratically with spatial compression to enable 32x compression while maintaining competitive performance on five text-to-image benchmarks.
The new models support custom dimensions and aspect ratios, with the Highspeed variant offering faster generation using the same API key.
The update is available across all ChatGPT tiers and the API, with Flare and Sunburst models supporting SVG exports and a new complexity parameter.
The new model features significant improvements over the Preview version and includes a detailed model card with training and architecture explanations.
The new adapters reduce image generation from 40 to 6 steps and remove the separate prompt-upsampling phase, saving 41 to 80 seconds per image.
The open-source tool supports 2D/3D scene composition and integrates models from Sora, Midjourney, and Grok under MIT and Apache-2.0 licenses.
Three new 'Aurora' model references briefly appeared in OpenAI's API and are being tested on Arena, with observers speculating they may be GPT-Image-3, though this remains a guess.
Krea has released Krea 3, a frontier image editing model claiming to be 10x faster and 3x cheaper than Nano Banana Pro, with a launch price of $0.06 per image.
The new model supports text-to-image, multi-reference editing, and bounding-box layout control, with distilled checkpoints generating 1024x1024 images in ~2 seconds on H100 GPUs.
The models support up to five reference images for edits and output sizes up to 1536 × 1536.
The 7B model generates 2K images and supports natural-language edits using an accelerated 8-step denoising schedule.
Lunara uses fewer than 10B active parameters and achieves the highest mean scores in blinded human evaluation across aesthetic quality, emotional resonance, and content integrity.
The new mode aims to improve prompt accuracy, typography, and coherence in generated images.
Apple researchers introduced Normalizing Trajectory Models (NTM), a framework that matches strong baselines in four sampling steps while retaining exact likelihood over the generative trajectory.
The model offers Flash-tier latency and cost while improving image generation and editing capabilities.
The model supports up to ten reference images for editing and five resolution tiers up to 4K.
FLUX 3 Image supports native 4K rendering and allows precise layout control via bounding boxes and up to 10 reference images.
Ideogram has released version 4.5 of its image model, designed to minimize visual degradation like pixel shifts and color drift during multi-turn edits while supporting high-resolution zoom editing up to 24.2 MP.
The new sampler requires no additional training and uses one model forward pass per denoising step to revise low-confidence tokens.
Applying FLUX.2 VAE and Muon improves training efficiency and strengthens understanding of Korean instructions
The new APIs allow programmatic generation of visuals using models from Google, OpenAI, ByteDance, and Creatify, available for Pro plans and above.
AntLing has released the open-source 6B image generation model 'Ming-Image-0.1-Design' and related agent skills.
Alibaba Qwen has released Qwen-Image-2.1, an image generation model that reduces parameters to 7B and supports transparency generation.
Qwen has released Qwen-Image-2.1, an open-source image model with 7 billion parameters that integrates generation and editing.