fofr / kolors

A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team

  • Public
  • 30.3K runs
  • L40S
  • GitHub
  • Paper
  • License

Input

string
Shift + Return to add a new line

Default: ""

string
Shift + Return to add a new line

Things you do not want to see in your image

Default: ""

integer
(minimum: 1, maximum: 10)

Number of images to generate

Default: 1

integer
(minimum: 512, maximum: 2048)

Width of the image

Default: 1024

integer
(minimum: 512, maximum: 2048)

Height of the image

Default: 1024

integer
(minimum: 1, maximum: 50)

Number of inference steps

Default: 25

number
(minimum: 0, maximum: 20)

Guidance scale

Default: 5

string

Scheduler

Default: "EulerDiscreteScheduler"

string

Format of the output images

Default: "webp"

integer
(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80

integer

Set a seed for reproducibility. Random by default.

Output

output
Generated in

This output was created using a different version of the model, fofr/kolors:05df67f7.

Run time and cost

This model costs approximately $0.044 to run on Replicate, or 22 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 46 seconds. The predict time for this model varies significantly based on the inputs.

Readme

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 proprietary 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 technical report.