Qwen-Image

A multimodal model for generating and editing images based on text prompts, part of the Qwen series of models. It demonstrates significant improvements in accurately rendering complex text (including Chinese) and performing advanced image-editing operations. The model possesses generalized capabilities in both image creation and editing, with an emphasis on preserving font details, composition, and contextual harmony of the text.

Key Features:

• Support for image generation based on text prompts in English and Chinese.
• Variable aspect ratios (e.g., 16:9, 4:3, 1:1) with specified dimensions.
• High detail preservation of text on images, maintaining layout and context for alphabetic languages (e.g., English) and logographic systems (e.g., Chinese).

---

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

• Text encoder: ~8.3B parameters,
• Transformer: ~20.4B parameters,
• VAE: ~126M parameters.

Total: ~28.8B 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: 04.08.2025
Parameters: 20B
Context: 128K
VRAM requirements: 14.8 GB using 4 bits quantization, 29.6 GB using 8 bits quantization, 59.1 GB using 16 bits quantization
Developer: Qwen
License: Apache 2.0

Use our pre-built public endpoints for free to test inference and explore Qwen-Image 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.