Tagged: image-generation

28 articles

Latest

Google Pics brings Nano Banana image editing to Docs and Slides

Inside the Annotated Diffusion Model: How DDPM Turns Pure Noise Into Images

ControlNet hits Diffusers: turn doodles into photos with 700M extra params

T2I-Adapters Slim Down SDXL Control: 79M Params vs ControlNet's Bulk

Würstchen hits 42x image compression, slashing AI training costs 16-fold

OpenAI adds transparent PNGs to GPT-Image-2 via API

New LCM LoRA cuts SDXL image generation from 7 seconds to 1 on a 3090

xAI's Imagine 2.0 scores 1,439 Elo, nipping at OpenAI's heels in image benchmarks

Alibaba's Qwen-Image-3.0 renders legible 10-pixel text and 9-panel infographics in one shot

PixelCNN++ ditches softmax for logistics, speeds up training

OT-GAN brings stable training to image generation benchmarks

DALL·E beta launches with 1M invites and a $15 pricing tier

DALL·E Can Now Extend Your Images Beyond the Frame

DALL·E drops its waitlist after 2M daily images

OpenAI's DALL·E API Goes Public, 4M Images a Day Already

DALL·E 3 lands in ChatGPT with a 99% accurate AI detective

OpenAI vets drop Consistency Models, hitting 3.55 FID in one step

Nvidia's sCM generates images 50x faster with just two steps

GPT-4o can now generate images — and it's a whole different beast

OpenAI bakes image gen into GPT-4o, and it can actually read

OpenAI puts ChatGPT's viral image maker into devs' hands via API

OpenAI quietly builds 3 holiday toys for NORAD’s Santa tracker

Hugging Face offloads VAE decoding to the cloud, slashing GPU memory for Flux and video models

Flux.1 beat Midjourney and DALL-E 3 in 2024 — here's the open-source shift it triggered

Stable Diffusion 3.5 hits Diffusers with an 8B model and a 4-step turbo variant

45,000 Human Votes Rank Midjourney, DALL·E, and Stable Diffusion Head-to-Head

SegMoE packs 4 Stable Diffusion models into one pipeline — and prompt accuracy jumps

Turn Any ComfyUI Workflow Into a Free Web App With This Trick