The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestBaidu1.0
BaiduText → Image

Baidu Releases 8B Text-to-Image Model ERNIE-Image

The large diffusion model from the Chinese tech giant is available under the commercially permissive Apache 2.0 license, a notable release for the community.

Apr 7, 2026
NotableApache 2.0
ERNIE-Image

Baidu has released ERNIE-Image, a powerful new text-to-image model, making it freely available to the open-source community. Part of the company's broader "ERNIE" family of foundational models, this release adds another significant player to the landscape of open generative AI.

What makes this release particularly notable is its scale and its license. At 8 billion parameters, ERNIE-Image is a substantial diffusion model. More importantly, it is available under the Apache 2.0 license, a fully permissive license that allows for commercial use, modification, and distribution. This stands in contrast to many other popular image models that carry more restrictive terms.

The model's weights and usage instructions are accessible on its Hugging Face repository. The release provides researchers and developers with a powerful, unrestricted foundation for building new applications, from creative tools to synthetic data generation.

Baidu's contribution marks a significant open-source release from a major Chinese technology firm. By providing a large-scale, commercially viable model, ERNIE-Image could help diversify the tooling available to the global AI community and foster new kinds of innovation outside the ecosystem of dominant Western tech companies.

Sources

  • baidu/ERNIE-Image

    Hugging Face

    Visit
OlderBlack Forest Labs Releases Open FLUX.2 Image DecoderBlack Forest Labs · Text → Image · 7 months agoNewerMiniMax Releases M2.7, an MoE Model with FP8 WeightsMiniMax · Text / LLM · 7 months ago

Get the model

Hugging Face

Specs

Parameters8B
Size16.1 GB
PrecisionBF16
ArchitectureErnieImagePipeline
LicenseAPACHE-2.0
Downloads1.9K
Likes685

Can you run it?

Runs on a laptop — about 9 GB at FP8.

  • BF16 (as published)

    24 GB GPU (RTX 3090 / 4090) · 32 GB Mac

    17.1 GB
  • FP8

    12 GB GPU (RTX 3060 / 4070) · 16 GB Mac

    9 GB
Your machine
  • Covers the published checkpoint; text encoders and VAE loaded alongside may add a few GB (many runtimes offload them to CPU).

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Text → Image

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Baidu

All Baidu releases →
Unlimited-OCR 2
Baidu/Vision-LanguageRuns anywhere

Baidu releases Unlimited-OCR 2 under MIT license

The multilingual vision-language model targets document text recognition and ships with a permissive license for commercial use.

Oct 26, 2026
Baidu/Vision-Language

Baidu's PP-OCRv6 packs 50-language OCR into tiny models

The latest release of PaddlePaddle's optical character recognition suite spans models from 1.5M to 34.5M parameters under an Apache 2.0 license.

Jun 22, 2026
Unlimited-OCR
Baidu/Vision-LanguageRuns anywhere

Baidu releases Unlimited-OCR under permissive MIT license

The Chinese tech giant's multilingual vision-language model targets text extraction across languages and document types.

Jun 19, 2026

More in Text → Image

All Text → Image →
Fibo 2.0-dev
Briaai/Text → ImageRuns on a laptop

Bria's Fibo 2.0 Brings Structured Prompts to Open Image AI

The new text-to-image and editing model leans on structured prompts and multi-reference inputs for more controllable generation.

Oct 18, 2026
FLUX.3 Image Klein
Black Forest Labs/Text → Image

Black Forest Labs ships FLUX.3 Image Klein for ComfyUI

The lab's latest open image model arrives packaged for ComfyUI with both generation and editing built in.

Oct 14, 2026
FLUX.3 Image Klein
Black Forest Labs/Text → ImageRuns on a laptop

Black Forest Labs ships FLUX.3 Image Klein

The latest open image model from the FLUX team handles both text-to-image generation and editing, and arrives ready to run in Diffusers.

Oct 13, 2026