Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team. Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to our <a target="_blank" rel="ugc" href="https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf">technical report</a>.

Kolors

kolors_v10.safetensors

v1.0

Kwai-Kolors/Kolors

diffusion_pytorch_model.fp16.safetensors

unet.fp16

kolors-base-1.0-vae-fp16

<img src="https://liblibai-online.liblib.cloud/img/b452266e79c349a3a3ee94b5f5f9d8e1/4d08e8798ff71e89a38fb8af50fb890eec5ceb69d586032875511412ecd8c794.png?x-oss-process=image/resize,w_1290,m_lfit/format,webp" alt="" data-href="https://liblibai-online.liblib.cloud/img/b452266e79c349a3a3ee94b5f5f9d8e1/4d08e8798ff71e89a38fb8af50fb890eec5ceb69d586032875511412ecd8c794.png?x-oss-process=image/resize,w_1290,m_lfit/format,webp" style="">Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team. Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to this <a href="https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf" target="" style="text-align: start;">technical report</a>.We have collected a comprehensive text-to-image evaluation dataset called KolorsPrompts for comparing Kolors with other state-of-the-art open-source and closed-source models. KolorsPrompts consists of over 1,000 prompts covering 14 categories and 12 evaluation dimensions. The evaluation process includes both human and machine assessment. In relevant benchmark evaluations, Kolors demonstrates highly competitive performance, meeting industry-leading standards.

Files with SHA256: 425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c