@heyshrutimishra: Baidu recently open-sourced ERNIE-Image, an 8B parameter model with weights available for commercial use. This is big. …
Summary
Baidu open-sourced ERNIE-Image, an 8B parameter text-to-image model with commercial-use weights, making it one of the few fully open and fine-tunable alternatives to closed models like Midjourney.
View Cached Full Text
Cached at: 04/21/26, 11:56 AM
Baidu recently open-sourced ERNIE-Image, an 8B parameter model with weights available for commercial use. This is big. Most leading text-to-image models right now are closed: • GPT-Image-1 • Seedream • Midjourney ERNIE-Image? Fully open. Fine-tunable. Runs on consumer GPUs.
Similar Articles
baidu/ERNIE-Image
Baidu releases ERNIE-Image, an open-weight text-to-image generation model with 8B parameters built on Diffusion Transformer architecture, achieving state-of-the-art performance among open-weight models with strong capabilities in text rendering, instruction following, and structured image generation.
baidu/ERNIE-Image-Turbo
Baidu releases ERNIE-Image-Turbo, a distilled text-to-image generation model that achieves fast generation in 8 inference steps while maintaining strong text rendering, instruction following, and structured image generation capabilities.
unsloth/ERNIE-Image-Turbo-GGUF
unsloth releases a GGUF quantized version of Baidu's ERNIE-Image-Turbo model using Unsloth Dynamic 2.0 methodology, enabling efficient text-to-image generation in 8 inference steps on consumer GPUs with 24GB VRAM.
New models possibly from Baidu (ERNIE) this month?
Speculative news about possible new ERNIE models from Baidu, hinted at via tweets and an upcoming Baidu Create 2026 event video.
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
The paper introduces i1, a 3B-parameter text-to-image diffusion model that achieves competitive performance with leading closed models while being fully open (weights, data, code). It provides insights from 300+ controlled experiments and offers a practical recipe for open research.