The Open Weights
LatestModelsLeaderboardsUpcomingCompanies
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
  • Upcoming launches

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • RSS feed
  • Newsletter

© 2026 The Open Weights. An independent publication.

Aggregated by Claude · written with Gemini · curated by humans.

LatestUnknownv0.1
UnknownText → Image

Illustrious-XL v0.1 Arrives as Anime Image Base

A 3.5B-parameter SDXL derivative aims to become the go-to foundation for anime-style text-to-image fine-tunes.

Sep 25, 2024
NotableOther
Unknown · Text → Image
Illustrious-XL v0.1

Illustrious-XL has landed in its first public release, v0.1, positioning itself as a dedicated base model for anime-style image generation. Built on the Stable Diffusion XL architecture and weighing in at roughly 3.5 billion parameters, the model is published on Civitai and targets creators who want a clean foundation rather than a heavily styled finished product.

The distinction matters. Base models are not meant to dazzle out of the box; they exist to be fine-tuned, merged, and adapted. By offering an SDXL-derived starting point tuned for anime aesthetics, Illustrious-XL slots into a workflow that thousands of hobbyists and small studios already use to produce specialized checkpoints and LoRAs.

Why it matters

The open image-generation ecosystem runs on shared foundations. A well-behaved base model can ripple outward into dozens of community derivatives, which is exactly the role Illustrious-XL is reaching for.

  • SDXL lineage means broad compatibility with existing tooling and pipelines.
  • Around 3.5B parameters keeps it accessible on consumer hardware.
  • An anime-focused base lowers the lift for downstream fine-tuners.

As a v0.1, expectations should be calibrated accordingly: this is an early checkpoint meant to seed further work. Its real test will be how many fine-tunes it inspires and how those build on the foundation in the months ahead.

Sources

  • Illustrious-XL

    civitai

    Visit

0 comments

Protected by Turnstile

No comments yet. Be the first to weigh in.

Get the model

civitai

Specs

Parameters3.5B
Context window—
LicenseOTHER
Downloads166.8K

Modalities

Text → Image

More in Text → Image

Ideogram
Ideogram 4.0
Ideogram 4.0
Ideogram/Text → Image

Ideogram 4.0: A 9.3B Open-Weight Text-to-Image Model

The new 9.3 billion parameter model uses a Diffusion Transformer architecture and excels at rendering coherent text within generated images.

May 30, 2026
ByteDance
Lance
Lance
ByteDance/Any-to-Any

ByteDance Releases Lance, a Unified Generative AI Model

The 3-billion-parameter model handles image and video generation, editing, and understanding from a single set of weights under a permissive license.

May 15, 2026
SenseTime
SenseNova U1 8B MoT Infographic
SenseNova U1 8B MoT Infographic
SenseTime/Any-to-Any

SenseTime Releases 8B 'Any-to-Any' Infographic Model

The new 8B-parameter SenseNova U1 model from SenseTime is designed for complex multimodal tasks, including the in-conversation generation and editing of infographics.

May 14, 2026