Kandinsky-5.0-I2I-Lite-sft-Diffusers

Kandinsky-5.0-I2I-Lite-sft-Diffusers is a image-to-image (I2I) model with 6 billion parameters, developed for modifying images based on text prompts. The model belongs to the Kandinsky 5.0 family, which includes models for generating video and images. Each model is designed with a focus on the Russian cultural context, natively processes prompts in both Russian and English, and generates text in Cyrillic and Latin scripts.

---

The model is a component of the video generation pipeline, consisting of:

• Text encoder: ~8.3B parameters,
• Text encoder 2: ~0.4B parameters,
• Transformer: ~6B parameters,
• VAE: ~83M parameters,

Total: ~14.8B parameters

---

The 'VRAM requirements' line is calculated based on the size of the weights in the specified precision, with an additional +10% coefficient for inference:
  model_parameters_count * bytes_per_parameter * 1.1 / 1024^3 
where model_parameters_count is number of model parameters, bytes_per_parameter is number of bytes used to store one parameter. For 16 bit = 2, 8 bit = 1, 4 bit = 0.5.

Announce Date: 19.11.2025
Parameters: 6B
VRAM requirements: 7.6 GB using 4 bits quantization, 15.2 GB using 8 bits quantization, 30.4 GB using 16 bits quantization
Developer: Sber AI
License: MIT

Use our pre-built public endpoints for free to test inference and explore Kandinsky-5.0-I2I-Lite-sft-Diffusers capabilities. You can obtain an API access token on the token management page after registration and verification.

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

• maximize endpoint performance,
• enable full context for long sequences,
• ensure top-tier security for data processing in an isolated, dedicated environment,
• use custom weights, such as fine-tuned models or LoRA adapters.

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.