Kandinsky 5.0 Image Lite: Text to Image
A lightweight 2B model that generates images from English and Russian prompts with high visual quality.
About
The 'Kandinsky 5.0 Image Lite: Text to Image' workflow is designed to generate high-quality images from text prompts in both English and Russian. This workflow leverages the Kandinsky model, a lightweight 2B parameter model, to produce visually appealing results efficiently. The workflow integrates several key nodes, including the 7aad998c-49e7-433f-bfb9-b1ac2680aa9e node for processing text inputs and generating images, the MarkdownNote node for annotating the workflow, and the SaveImage node for storing the generated images.
What you provide
- Reading the workflow
Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.
Try in CloudQuestions & answers
Currently, the workflow is optimized for English and Russian prompts. Other languages may not produce accurate results.
A system with a capable GPU and sufficient memory is recommended to efficiently run the Kandinsky model and handle the text encoders.
Ensure that your text prompts are clear and descriptive. Experimenting with different phrasing can also yield better results.
Related workflows
- Kandinsky
Kandinsky 5.0 Video Lite Image to Video
- Kandinsky
Kandinsky 5.0 Video Lite Text to Video
- Z-Image-Turbo
1.1 Starter - Text to Image
- Z-Image-Turbo
2.1 Creator - Diffusion Basics
- Nano Banana 2 Text-to-Image
3x3 Contact Sheet
- Partner node
AI on the Lot 2026 - Z-Image Turbo - t2i
- Partner node
Anima Base v1: Text to Image
- Capybara
Capybara: Text to Image
- Google Gemini Image, Nano Banana Pro
Character × 4 Scene Explorer
- Chroma
Chroma1 Radiance Text to Image
- Chroma, Flux
Chroma: Text to Image
- Flux, Flux.1
Flux.1 [Pro]: Text to Image