Photorealistic text-to-image diffusion model for creators
Kolors is a cutting-edge text-to-image model powered by latent diffusion. Trained on billions of pairs, it excels in visual quality, complex semantics, and text rendering, outperforming both open and closed-source models.
Hi Product Hunt! 👋🏽
I‘m Knox from Kling AI, today I’m excited to share our latest product we have been actively building, Kolors, a cutting-edge text-to-image model powered by latent diffusion.
We have collected a comprehensive text-to-image evaluation dataset named KolorsPrompts to compare Kolors with other state-of-the-art open models and closed-source models. KolorsPrompts includes over 1,000 prompts across 14 catagories and 12 evaluation dimensions. The evaluation process incorporates both human and machine assessments. In relevant benchmark evaluations, Kolors demonstrated highly competitive performance, achieving industry-leading standards.
For the human evaluation, we invited 50 imagery experts to conduct comparative evaluations of the results generated by different models. The experts rated the generated images based on three criteria: visual appeal, text faithfulness, and overall satisfaction. In the evaluation, Kolors achieved the highest overall satisfaction score and significantly led in visual appeal compared to other models.
For more experimental results and details, please refer to our [technical report](https://github.com/Kwai-Kolors/K...).
Let me know if you have any feedback or questions - we’re constantly working on improving our product for you! 💫
Cheers,
Knox
