The template's own example, on five seeds
From MOSS-Image add-ons, tested locally






- Model
- MOSS-Image SFT (moss_image_sft_int8_convrot.safetensors)
- Output
- 1024×1024
- Sampling
- 25 steps, CFG 2.5, er_sde / simple
- Seeds
- 101, 7, 42, 300, 777
- Seed 101
- 43.0 s, peak VRAM 10.7 GiB
- Ran on
- RTX 3060, 12GB (local)
The big title and the knight land, but the small paragraphs wander out of their boxes, and that happened on every seed I tried.
Dark fantasy editorial poster in a lush overgrown ruin: a knight in moss-covered plate armour in a heroic kneeling pose, torso upright and head lifted, one hand gripping a massive greatsword planted point-down beside him, the other forearm on his raised knee, a dense bouquet of daisies and pink roses growing out of the open helmet instead of a face, ivy and crumbling columns behind, petals drifting in the air, soft volumetric light from above, deep green and moss palette with muted cream type.
[
{
"x": 0,
"y": 56,
"width": 1024,
"height": 333,
"metadata": {
"type": "text",
"text": "MOSS",
"desc": "Across the top of the poster, enormous cream serif capitals spell , with oversized high-contrast letterforms cropped by both the left and right edges so the word extends beyond the composition. The typography is flat, bold, and sharply defined against a dark background",
"palette": []
}
},
{
"x": 143,
"y": 184,
"width": 778,
"height": 840,
"metadata": {
"type": "obj",
"text": "",
"desc": "A knight in moss-covered steel plate armour strikes a heroic kneeling pose: one knee planted on the ground, the other leg bent forward with the foot braced, torso upright and chest pushed forward, shoulders back, head lifted and facing straight ahead, one gauntleted hand gripping the hilt of a massive greatsword planted point-down beside him, the other forearm resting on his raised knee, the broad blade weathered and rust-streaked, a dense bouquet of white daisies and pink roses bursting from the open helmet instead of a face, ivy, ferns and tumbled stonework behind him",
"palette": []
}
},
{
"x": 31,
"y": 26,
"width": 205,
"height": 67,
"metadata": {
"type": "text",
"text": "MOSS IMAGE\nPROJECT",
"desc": "In the top-left corner, two lines of tiny cream uppercase sans-serif type read , set in a compact left-aligned block with tight line spacing. The surrounding area remains dark and unobstructed",
"palette": []
}
},
{
"x": 61,
"y": 655,
"width": 276,
"height": 143,
"metadata": {
"type": "text",
"text": "\"ALL THAT FADES\nWAS NEVER MEANT\nTO REMAIN\"",
"desc": "A compact three-line text block in the upper-left portion of the specified region, reading in small cream-colored uppercase serif lettering. The words are enclosed by thin cream quotation marks at the beginning and end, with centered line alignment, tight line spacing, and a subtle dark shadow for legibility against the underlying background",
"palette": []
}
},
{
"x": 666,
"y": 440,
"width": 358,
"height": 174,
"metadata": {
"type": "text",
"text": "EVEN THE ARMOUR CANNOT CARRY EVERYTHING.\nWHAT HAS NO GROUND READS THE DEEPEST.",
"desc": "A compact paragraph of tiny cream uppercase serif lettering on the right, arranged across two tightly spaced lines and reading The text sits against a dark background with restrained line spacing and clean margins",
"palette": []
}
},
{
"x": 492,
"y": 768,
"width": 543,
"height": 225,
"metadata": {
"type": "text",
"text": "\"WITHIN THE HOLLOW,\nSOMETHING ALWAYS\nTAKES ROOT.\"",
"desc": "Large cream serif capitals reading are arranged as three centered lines at the bottom right, with generous line spacing and a thin dark quotation mark enclosing the text block",
"palette": []
}
}
]nsfw, worst quality, bad anatomy, watermark, jpeg artifact
Notes
The boxes are drawn in the template's Create Bounding Boxes node. Each one is a text box (the exact words to spell and how they should look) or an object box (a description), and the MOSS-Image Layout Prompt node turns the caption and the boxes into the layout prompt the model was trained on. The Caption and Boxes tabs are exactly what those two nodes were given.
Boxes 04 and 05, the two small quotes, are drawn on each result. The other seeds use the same workflow with only the seed changed.
Comfy-Org workflow templates (the MOSS-Image templates ship with ComfyUI)
Run it yourself
This test loads no input files. Put the models below in place and drag the workflow onto ComfyUI.
| File | Put it in | Size |
|---|---|---|
| moss_image_sft_int8_convrot.safetensors | models/diffusion_models | 5.4 GB |
| qwen3.5_9b_w4a8_gptq.safetensors | models/text_encoders | 7.3 GB |
| flux2-vae_small.safetensors | models/vae | 249.5 MB |
No custom nodes. Every node is part of ComfyUI 0.43.1 (frontend 1.57.6, templates 0.11.100).