Kuaishou Kolors

Name: Kuaishou Kolors
Brand: Community
SKU: kolors-kuaishou
Price: 0.0889 USD
Availability: InStock

Image generationAvailable

by Communitykolors-kuaishou

Kuaishou's bilingual (CN/EN) latent diffusion text-to-image model with strong text rendering.

Try it Get API key Compare

Price: ≈ $0.0889/run
Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4
Resolution: 1024×1024, 1024×1536, 1536×1024
Input → output: Text → Image
Developer: Community
Updated: September 23, 2026

Playground

Try Kuaishou Kolors

Input & output

≈ $0.0889/run

Prompt

0 / 2,000

What to generate (CN or EN)

Size(optional)

Aspect ratio(optional)

Advanced settings (4)

Negative prompt(optional)

0 / 1,000

What to avoid

Seed(optional)

Optional seed for reproducibility

Guidance scale(optional)1–20

Steps(optional)1–100

⌘/Ctrl + Enter

Output

Your image appears here.

This run

about $0.0889 · 8.89 credits

$0.2665 (26.65 credits) are reserved at the start; the actual GPU time is billed.

For accounts without a purchase: runs above 2 credits need a top-up.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits.

Examples

Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.

Open full size
Prompt
Expressive illustration of a pug puppy on a Water Slide basked in summer heat
Settings
width

1024
height

1024
Open full size
Input
Prompt
City of mini robots in Paris, rainy weather, night
Settings
width

1024
height

1024
Open full size
Prompt
an illustration of a woman walking in times square, in the style of jessica rabbit
Settings
width

1024
height

1024

About Kuaishou Kolors

TL;DRAs of September 23, 2026

Kuaishou Kolors is a model by Community in the Image generation category. On Railwail, Kuaishou Kolors costs ≈ $0.0889 per run. Supported aspect ratios: 1:1, 16:9, 9:16, 4:3, and 3:4.

Background

About Kuaishou (Kolors Team)

Founded 2011 · Beijing, China

Kuaishou Technology (快手) is a Chinese short-video platform founded in 2011 in Beijing by Su Hua and Cheng Yixiao, listed on the Hong Kong Stock Exchange since 2021. Its AI research division, often referred to as the Kuaishou KwaiVGI or Kling AI team, has produced several generative-media foundation models including Kling (video) and Kolors (image). Kolors was open-sourced in July 2024 with weights released on Hugging Face and GitHub (Kwai-Kolors/Kolors). The model is positioned as the best open Chinese-English bilingual text-to-image model, particularly strong on Chinese-language prompts, calligraphy and culturally specific content.

Visit Kuaishou (Kolors Team)

Architecture

Latent diffusion U-Net with ChatGLM3-6B text encoder (bilingual Chinese-English)

Kolors is a latent diffusion text-to-image model released open-source by Kuaishou in July 2024. The architecture follows the Stable Diffusion XL family — a latent-space U-Net with cross-attention conditioning on text embeddings — but replaces the standard CLIP text encoder with the much larger ChatGLM3-6B, a bilingual Chinese-English instruction-tuned LLM developed by Tsinghua KEG and Zhipu AI. This gives Kolors strong understanding of Chinese-language prompts, idioms, calligraphy and culturally specific content (food, festivals, Chinese architecture, traditional clothing) that Western models like SDXL and FLUX often struggle with. The U-Net has ~2.6B parameters and is trained at 1024x1024 resolution with the standard noise-prediction objective. Kuaishou also released a Kolors-Inpainting variant and a Kolors-ControlNet collection (Canny/Depth). The model is open-source under the Apache 2.0 license, making it the leading commercial-use open bilingual model.

Parameters: ~2.6B U-Net + 6B ChatGLM3 text encoder
Context: 256 tokens

Capabilities

Best-in-class understanding of Chinese-language prompts
Strong English performance comparable to SDXL
1024x1024 native resolution
Open weights under Apache 2.0
Excellent rendering of Chinese characters and calligraphy
Culturally accurate Chinese-food, festival, architecture and clothing imagery
Companion models: Kolors-Inpainting, Kolors-ControlNet (Canny/Depth/Pose)
Best for: Chinese-market apps, bilingual creative tools, culturally specific content, self-hosted Chinese services.

Training & license

Trained on a large mixed Chinese-English image-text corpus including high-quality Chinese-captioned data. Exact composition is not disclosed.

License: Apache 2.0 — open weights, full commercial use permitted including redistribution and derivatives.

Safety testing: Internal safety filters; the model adheres to Chinese content regulations including filters for sensitive political content. Operators outside China should apply their own moderation.

Known limitations

Image quality below FLUX 1.1 [pro] on photorealism
Smaller model than SD3.5 Large or FLUX
Some Chinese-regulatory filters baked into training
Open weights have no integrated safety classifier

Research papers

Pricing

Prices in US dollars. Usage is charged from prepaid credits.

Typical run (≈ 53 s on A100 (80GB))	$0.0889 per run
GPU time (A100 (80GB))	$0.00168 per GPU second

Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
1 credit = $0.01

Cost calculator

Price calculator

GPU seconds per run

Typical according to the provider: about 52.9 s

Runs

Total

$8.89

889 credits

Per run

$0.0889 · 8.89 credits

Billed by the actual GPU time; this is an estimate.

API

Call Kuaishou Kolors with your Railwail API key. Use this model ID in the request:

kolors-kuaishouAPI documentation Get an API key

curl https://railwail.com/api/v1/images/generations \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kolors-kuaishou",
    "prompt": "A lighthouse on a rocky coast at sunset, photorealistic"
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

image = client.images.generate(
    model="kolors-kuaishou",
    prompt="A lighthouse on a rocky coast at sunset, photorealistic",
)

print(image.data[0].url)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const image = await client.images.generate({
  model: "kolors-kuaishou",
  prompt: "A lighthouse on a rocky coast at sunset, photorealistic"
});

console.log(image.data[0].url);

// npm install railwail
import railwail from "railwail";

const rw = railwail(process.env.RAILWAIL_API_KEY);

const res = await rw.image("kolors-kuaishou", "A lighthouse on a rocky coast at sunset, photorealistic");

console.log(res.data[0].url);

Set your key as RAILWAIL_API_KEYCreate API key

Specifications

Model ID: kolors-kuaishou
Developer: Community
Category: Image generation
Input: Text
Output: Image
Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4
Resolution: 1024×1024, 1024×1536, 1536×1024
Billing: By usage (tokens or GPU time)
Model size: ~2.6B U-Net + 6B ChatGLM3 text encoder
License: Apache 2.0 — open weights, full commercial use permitted including redistribution and derivatives.
Catalog entry updated: September 23, 2026

Input parameters

Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.

ParameterTypeDefaultAllowed values

promptrequired
What to generate (CN or EN)
Type: Text
Default: –
Allowed values: up to 2,000 characters
seed
Optional seed for reproducibility
Type: Integer
Default: –
Allowed values: –
size
Type: Choice
Default: 1024x1024
Allowed values: 1024x1024, 1024x1536, or 1536x1024
aspect_ratio
Type: Choice
Default: 1:1
Allowed values: 1:1, 16:9, 9:16, 4:3, or 3:4
guidance_scale
Type: Number
Default: 5
Allowed values: 1 to 20
negative_prompt
What to avoid
Type: Text
Default: –
Allowed values: up to 1,000 characters
num_inference_steps
Type: Integer
Default: 30
Allowed values: 1 to 100

Use cases

What it is used for

Chinese-market consumer creative apps
Bilingual marketing-asset generation
Culturally specific imagery (food, festivals, fashion)
Self-hosted Chinese-language services
Chinese e-commerce product imagery
Educational content for Chinese learners

Related guides

Text to Image Models

All models in Image generation

Frequently asked questions

What is Kuaishou Kolors?

Kuaishou Kolors is a model by Community in the Image generation category. On Railwail you can call it with an API key through the Railwail API.

How much does Kuaishou Kolors cost on Railwail?

On Railwail, Kuaishou Kolors costs ≈ $0.0889 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.

Which settings does Kuaishou Kolors support?

According to its input schema, Kuaishou Kolors knows these parameters: prompt (up to 2,000 characters), seed, size (1024x1024, 1024x1536, or 1536x1024), aspect_ratio (1:1, 16:9, 9:16, 4:3, or 3:4), guidance_scale (1 to 20), negative_prompt (up to 1,000 characters), and num_inference_steps (1 to 100).

How fast is Kuaishou Kolors?

There are not enough measured runs of Kuaishou Kolors on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is Kuaishou Kolors better than FLUX 1.1 Pro?

That depends on the task. Kuaishou Kolors (Community) and FLUX 1.1 Pro (Black Forest Labs) are both models in the Image generation category. The comparison page shows their prices and specifications side by side.

Compare Kuaishou Kolors and FLUX 1.1 Pro

How do I use Kuaishou Kolors through the API?

Create a Railwail API key and send your request with the model ID kolors-kuaishou. Code examples for curl, Python and JavaScript are in the API section of this page.

Comparable models

All in this category

Icons (SDXL Flat Pop)Community
SDXL fine-tune by galleri5 for slick flat icons and pop constructivist graphics with thick edges. Trained on Bing generations, it produces clean single-subject icon art that suits app icons, badges and UI glyphs. Raster output, not true vector.
≈ $0.0094/run
89 % cheaper per unit
Compare Kuaishou Kolors vs. Icons (SDXL Flat Pop)
InstantIDCommunity
InstantID makes realistic portraits of a real person from a single reference photo without per-user training. Combines a face encoder with an IdentityNet adapter on SDXL to keep identity and pose while following a text prompt, so it is fast and tuning-free.
≈ $0.084/run
6 % cheaper per unit
Compare Kuaishou Kolors vs. InstantID
Sticker MakerCommunity
fofr's sticker generator that outputs graphics with transparent backgrounds, so the result drops straight into chat apps or print sheets. Runs an SDXL-based pipeline at high speed (default 17 steps) and returns die-cut style art without manual background removal.
≈ $0.0055/run
94 % cheaper per unit
Compare Kuaishou Kolors vs. Sticker Maker

Use Kuaishou Kolors via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.

Get API key Browse all models