Generate images by describing object positions in JSON — MOSS-Image walkthrough

Описание и применение

<p>Most image generation models understand prompts like "a red ball on the left and a blue cube on the right." The problem is, they understand it maybe half the time. The ball ends up on the right, or both objects merge into one, or the cube turns red too.</p> <p>Last week OpenMOSS released MOSS-Image, a 5B diffusion model under Apache 2.0 that addresses this with a different approach: describe object positions in JSON, and the model respects the coordinates.</p> <p>I put together a ComfyUI workflow and a prompt collection. Here's a walkthrough of how the JSON layout system works.</p> <h2> Wha

Задача

<p>Most image generation models understand prompts like "a red ball on the left and a blue cube on the right." The problem is, they understand it maybe half the time. The ball ends up on the right, or both objects merge into one, or the cube turns red too.</p> <p>Last week OpenMOSS released MOSS-Image, a 5B diffusion model under Apache 2.0 that addresses this with a different approach: describe object positions in JSON, and the model respects the coordinates.</p> <p>I put together a ComfyUI workflow and a prompt collection. Here's a walkthrough of how the JSON layout system works.</p> <h2> Wha

Результат

<p>Most image generation models understand prompts like "a red ball on the left and a blue cube on the right." The problem is, they understand it maybe half the time. The ball ends up on the right, or both objects merge into one, or the cube turns red too.</p> <p>Last week OpenMOSS released MOSS-Image, a 5B diffusion model under Apache 2.0 that addresses this with a different approach: describe object positions in JSON, and the model respects the coordinates.</p> <p>I put together a ComfyUI workflow and a prompt collection. Here's a walkthrough of how the JSON layout system works.</p> <h2> Wha

Доказательства

Generate images by describing object positions in JSON — MOSS-Image walkthrough

Источник