Image generation

Last updated: November 1, 2024

Our image generation leaderboard evaluates AI models on their ability to generate high-quality images from textual descriptions. We assess various factors based on the project's specific criteria.

Human preference evaluation

Diverse pool of US-based Alignerrs, including generalists and creative artists

Consensus of three Alignerrs per task

Standardized instructions and ontology for consistent evaluations

Carefully curated prompt generation process, balancing creativity and clarity

Overall preference

Prompt alignment

Visual appeal

Examples

PROMPT

Serene watercolor: cozy cottage nestled in lush garden. Gentle sunlight, soft pastels. Low-angle view emphasizing inviting doorway. Warm, welcoming atmosphere.

Ideogram 2.0

DALL•E 3

Flux 1.1 pro

Imagen 3

Stablediffusion 3.5

Want us to evaluate your model?

If you’d like to evaluate your model as part of the next leaderboard update, contact us at leaderboard@labelbox.com.