MOSS-Image-SFT

Use it to generate images from text prompts, including organized layouts with readable text and specified element positions.

Availability

Code and model weights are publicly available; available through the MOSI API Platform

Pricing model

Not established

Deployment

Run locally using the Python pipeline or Gradio app

Privacy

Not established

Licence

Apache License, Version 2.0

• It supports natural-language prompts, tag sequences, and JSON layouts. ^[1]

  prompts, tag sequences, and JSON layouts for controlling text placement and

• The model is available on Hugging Face and ModelScope.
• The quick start requires Python 3.10 or later and an NVIDIA GPU with CUDA support. ^[1]

  Use Python 3.10 or later and an NVIDIA GPU with CUDA support.

• The model weights and custom pipeline code are downloaded and cached automatically, and a local model directory can also be used. ^[1]

  The model and custom pipeline code are downloaded and cached automatically.

• The model weights and bundled inference code are released under the Apache License, Version 2.0. ^[1]

  The model weights and bundled inference code are released under the

• Code and model weights for MOSS-Image-SFT are publicly available. ^[2]

  Code and model weights are publicly available.

• MOSS-Image-SFT is fine-tuned from MOSS-Image-Base on curated data. ^[2]

  | [MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT) · [ModelScope](https://modelscope.cn/models/openmoss/MOSS-Image-SFT) | Fine-tuned from MOSS-Image-Base on curated data |

• MOSS-Image supports layout control for text and visual elements. ^[1]
• MOSS-Image accepts text prompts of up to 4K tokens.
• The MOSS-Image series is available through the MOSI API Platform.