# MOSS Aria-BF16Cinematic atmosphere. Tactile detail. Images with a story to tell.MOSS Aria is my full fine-tune of [OpenMOSS-Team/MOSS-Image-Base](<a target="_blank" rel="ugc" href="https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base">https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base</a>), trained for 5,000 steps on an NVIDIA H200. I developed it around expressive subjects, coherent anatomy, layered environments, and the small textures and particles that give a scene its sense of depth.The gallery reflects that range: intimate portraits, wildlife and macro nature, weathered science fiction, and playful fantasy. The goal is a frame that feels composed as a whole while still inviting a closer look.## The BF16 releaseThis download is the original full fine-tune in Safetensors format. It contains BF16 transformer weights, with one small F32 auxiliary tensor. It is a complete fine-tune of the MOSS-Image transformer, not a LoRA. The text encoder and VAE are separate components and are not included in this file.| Detail | Value || --- | --- || Base architecture | MOSS-Image || Base model | OpenMOSS-Team/MOSS-Image-Base || Training | Full fine-tune, 5,000 steps || Training hardware | NVIDIA H200 || Download | Safetensors, approximately 9.47 GiB || SHA-256 | <code>3f331a97fc184cec752ef0a7f1c46187726a907bc5ffcb4db8b19902282d9fc1</code> |Use a workflow that supports MOSS-Image and provide the corresponding text encoder and VAE. The [official MOSS-Image-Base page](<a target="_blank" rel="ugc" href="https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base">https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base</a>) links to its setup and ComfyUI guidance.## About the galleryI created the gallery images in Draw Things with the corresponding converted MOSS Aria model. They show the visual character of this training run. Because they were rendered with a Draw Things conversion, they are illustrative examples rather than direct BF16 inference tests. Generation prompts and settings are not listed here.## Credit and change noticeMOSS Aria is derived from MOSS-Image-Base by OpenMOSS. The base model weights are released under [Apache License 2.0](<a target="_blank" rel="ugc" href="https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base/blob/main/LICENSE">https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base/blob/main/LICENSE</a>). The transformer weights in this release were modified through full fine-tuning. Please credit OpenMOSS for the base model.

MOSS Aria BF16

<code>Full BF16 fine-tune of MOSS-Image-Base, trained for 5,000 steps on an NVIDIA H200. Full transformer checkpoint; not a LoRA.</code>

Files with SHA256: 3f331a97fc184cec752ef0a7f1c46187726a907bc5ffcb4db8b19902282d9fc1