Note: All model files below must be downloaded via the LM Downloader client. If you do not have the client, Download >>>
Its core capability is image-to-image style transfer: take an input reference image and convert its style into realistic portrait photography. It preserves the original pose, composition and subject structure of the reference image while improving facial features, skin and material details to produce photorealistic outputs. There is no mandatory trigger word for this model. Chinese positive prompts can be used to constrain details, lighting and materials to further enhance realism.
| Name | Size | Target Dir |
|---|---|---|
| Qwen-Image-2.1_A2R_Mugi_v2.5_c1-st5000.safetensors | 167.83 MB | loras |