An anime character in layout boxes, on Base
From MOSS-Image add-ons, tested locally







- Model
- MOSS-Image Base (moss_image_base_int8_convrot.safetensors)
- Output
- 1024×1024
- Sampling
- 25 steps, CFG 2.5, er_sde / simple
- Seeds
- 7, 42, 101, 21, 300, 777
- Seed 7
- 56.5 s, peak VRAM 10.4 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
Picture 1
Freya, anime characterAnime character drawn from the Freya cast photo with the Qwen-Image 2.1 edit template (not MOSS)Download PNG0.8 MB
The board, the route number and the poster land where they should, the spelling holds and the character stays in her box. Her face is close on both models, but neither keeps it exactly the same, so I wouldn't count on it for the same character from one picture to the next.
Same character and art style as Picture 1.
Anime illustration of a city bus stop on a rainy night. An orange LED arrival board hangs from the shelter roof at the top left. A round blue route sign on a pole stands at the top right. Under the glass shelter the woman from Picture 1 stands on the left, and beside her a small paper poster is taped to the glass at chest height. Wet pavement reflecting red and blue neon, rain streaks in the light of the street lamps. Cel shading, clean line art.
[
{
"x": 40,
"y": 30,
"width": 560,
"height": 110,
"metadata": {
"type": "text",
"text": "NEXT BUS 4 MIN",
"desc": "Glowing orange LED dot-matrix capitals on a black panel",
"palette": []
}
},
{
"x": 680,
"y": 30,
"width": 300,
"height": 210,
"metadata": {
"type": "text",
"text": "ROUTE 42\nHARBOUR ST",
"desc": "White capitals on a round blue sign, the number large and the street name smaller below it",
"palette": []
}
},
{
"x": 40,
"y": 250,
"width": 360,
"height": 760,
"metadata": {
"type": "obj",
"text": "",
"desc": "The woman from Picture 1, arms folded, looking at the camera. Long straight blonde hair, blue eyes, sage green tank top, white jeans",
"palette": []
}
},
{
"x": 420,
"y": 330,
"width": 184,
"height": 300,
"metadata": {
"type": "text",
"text": "LATE\nSHOW\nTONIGHT",
"desc": "Bold red capitals on a white paper poster, one word per line",
"palette": []
}
}
]Notes
The boxes say where things go and the picture says who she is. The boxes are drawn on each result. The other seeds use the same workflow with only the seed changed.
The CharRef card says it was trained on Base; the SFT run is the same graph on the SFT model.
Run it yourself
Download everything for this test (.zip, 0.8 MB). It holds the workflow, every input it loads and a README. Copy the inputs into ComfyUI/input, put the models below in place and drag the workflow onto ComfyUI.
| File | Put it in | Size |
|---|---|---|
| moss_image_base_int8_convrot.safetensors | models/diffusion_models | 5.4 GB |
| moss_image_charref_v2.safetensors | models/loras | 148.7 MB |
| 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).