By using this website, you agree to our Privacy Policy and Terms of Use.
Accept
Craftium.AICraftium.AICraftium.AI
  • Home
  • News
  • Catalog
  • Collections
  • Blog
Font ResizerAa
Craftium.AICraftium.AI
Font ResizerAa
Пошук
  • Home
  • News
  • Catalog
  • Collections
  • Blog
Follow US
  • Terms of Use
  • Privacy Policy
  • Copyright
  • Feedback
© 2024-2025 Craftium.AI.

A new mysterious image generation model has outperformed market leaders

The red_panda model has outperformed Flux1.1 Pro from Black Forest Labs, taking the lead on the Artificial Analysis platform.

Igor Lev
Igor Lev
Published: 29.10.2024
News
red_panda
Example of an image generated by the red_panda modeldeedydas
SHARE

On the Artificial Analysis platform, where the quality of generative models for image creation is compared, a mysterious AI called “red_panda” has taken the lead. The model has surpassed such well-known solutions as Midjourney, Black Forest Labs, and OpenAI, and is ahead of its closest competitor — Flux1.1 Pro from Black Forest Labs — by about 40 points according to the Elo system, which is used to assess the relative level of models.

A new mysterious image generation model has outperformed market leaders
Model rankings on Artificial Analysis

Artificial Analysis, similar in principle to Chatbot Arena, uses a crowdsourcing approach: models are tested through user ratings. Two models receive the same prompt for image creation, and users choose which picture better matches the request.

In addition to leading in quality, “red_panda” also stands out for its speed — it needs only seven seconds to generate an image, which is several orders of magnitude faster than DALL-E 3 from OpenAI, which takes over 100 times longer to create an image.

The model raises many questions. Its name hints at a Chinese origin, and users are actively discussing which tech giant it might belong to. The issue of openness is also being raised — will red_panda be available to the public?

Grok will receive infinite image generation and audio videos
Dreamina AI
Alibaba introduced the Qwen VLo model for step-by-step image generation
FLUX.1 context [dev] simplifies image generation for all users
The new Imagen 4 model is already being tested with the Gemini API
TAGGED:Image generationRed PandaText to image
SOURCES:deedydas
Leave a Comment

Leave a Reply Cancel reply

Follow us

XFollow
YoutubeSubscribe
TelegramFollow
MediumFollow

Popular News

Mistral AI
Mistral offers the open language model Voxtral for speech
17.07.2025
Grok 4
Grok 4 from xAI promises to become the new standard for developers
06.07.2025
ChatGPT Agent
OpenAI introduced ChatGPT Agent, allowing AI to delegate complex tasks
18.07.2025
Siri
Apple Tests OpenAI and Anthropic Models for Next-Generation Siri
01.07.2025
AI machine
The number of AI users reaches 1.8 billion, only 3% use it for a fee
01.07.2025

Читайте також

Firefly
News

Firefly by Adobe is now available for iOS and Android

20.06.2025
ChatGPT WhatsApp
News

ChatGPT Image Generation Now Available on WhatsApp

18.06.2025
Adobe Firefly
News

Adobe Firefly App Now Available for Everyone

17.06.2025

Craftium AI is a team that closely follows the development of generative AI, applies it in their creative work, and eagerly shares their own discoveries.

Navigation

  • News
  • Reviews
  • Collections
  • Blog

Useful

  • Terms of Use
  • Privacy Policy
  • Copyright
  • Feedback

Subscribe for AI news, tips, and guides to ignite creativity and enhance productivity.

By subscribing, you accept our Privacy Policy and Terms of Use.

Craftium.AICraftium.AI
Follow US
© 2024-2025 Craftium.AI
Subscribe
Level Up with AI!
Get inspired with impactful news, smart tips and creative guides delivered directly to your inbox.

By subscribing, you accept our Privacy Policy and Terms of Use.

Welcome Back!

Sign in to your account

Username or Email Address
Password

Lost your password?