Qwen-Image-Edit-2511

Qwen-Image-Edit-2511 is an enhanced image-to-image generation model, succeeding Qwen-Image-Edit-2509.

Key improvements:

• mitigated image drift, improved character consistency,
• Preserves identity and visual characteristics during imaginative edits of input portraits, with enhanced multi-person group photo consistency for high-fidelity fusion of separate person images.
• LoRA Integration: Directly incorporates popular community-created LoRAs (e.g., lighting enhancement, viewpoint generation) without requiring additional tuning, expanding expressive capabilities.
• Industrial Design Applications: Supports batch product design and material replacement for industrial components.
• Geometric Reasoning: Generates auxiliary construction lines for design or annotation purposes.

---

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

Announce Date: 17.12.2025
Parameters: 20B
Developer: Qwen
Diffusers Version: 0.36.0.dev0
vLLM-Omni Version: 0.12.0rc1
License: Apache 2.0

Use our pre-built public endpoints for free to test inference and explore Qwen-Image-Edit-2511 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.