Total runs:
213.5K
Run Growth:
125.2K
Growth Rate:
58.61%
Sponsored by
ThumbnailCreator.com
OpenMOSS-Team / MOSS-Image-SFT
Model's Last Updated: October 19 2026
text-to-image
Introduction of MOSS-Image-SFT
Model Details of MOSS-Image-SFT
MOSS-Image-SFT
MOSS-Image-SFT is a supervised fine-tuned text-to-image model in the MOSS-Image family from OpenMOSS, derived from MOSS-Image-Base . It uses the same architecture and inference pipeline, supporting natural-language prompts, tag sequences, and JSON layouts for controlling text placement and object arrangement.
Base vs. SFT
In this example, SFT produces clearer text grouping and a more organized whiteboard layout.
| MOSS-Image-Base | MOSS-Image-SFT |
|---|---|
|
|
Quick start
Use Python 3.10 or later and an NVIDIA GPU with CUDA support. Install a PyTorch 2.9 or later build compatible with your CUDA environment, then install:
pip install "diffusers>=0.38" "transformers>=5.3" "accelerate>=1.10" "safetensors>=0.6" "Pillow>=10"
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
"OpenMOSS-Team/MOSS-Image-SFT",
custom_pipeline="pipeline_moss_image",
trust_remote_code=True,
torch_dtype={"default": torch.bfloat16, "vae": torch.float32},
)
pipe.scheduler = type(pipe.scheduler).from_config(pipe.scheduler.config)
pipe.to("cuda")
prompt = '''A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:
"记得买牛奶和鸡蛋！
牛奶两盒，鸡蛋一打。
顺便带一袋面包。"'''
image = pipe(
prompt,
height=1024,
width=1024,
num_inference_steps=50,
guidance_scale=3.0,
uncond_skip_layers=[22],
generator=torch.Generator("cpu").manual_seed(42),
).images[0]
image.save("refrigerator_note.png")
The model and custom pipeline code are downloaded and cached automatically. You
can also pass a complete local model directory to
from_pretrained
.
The transformer and text encoder use bfloat16; the VAE and initial noise use
float32. The bundled VAE uses the FLUX.2 small decoder.
For the Gradio interface, CPU offload, and compilation options, follow the project quick start . For ComfyUI, search for MOSS-Image in ComfyUI Manager to install the native plugin. Integration into the official ComfyUI repository is in progress. See the installation and usage guide and example workflow .
Sampling settings
| Setting | Default |
|---|---|
| Sampler | Flow-matching Euler |
| Steps | 50 |
| CFG | 3 |
| Shift | 5 |
| Layer skipping | Negative branch, layer index 22 (zero-based) |
| Negative prompt | Empty |
The default guidance uses two transformer forwards per step. Pass
uncond_skip_layers=[]
to disable negative-branch skipping, or set
negative_prompt
to provide a negative prompt. Python API image dimensions must
be positive multiples of 16.
See the user guide for resolution, sampling, prompt, and LoRA training recommendations.
Prompt enhancer skill
The MOSS-Image Prompt Enhancer turns image ideas into detailed captions or spatial Layout prompts. It is designed for GPT-6-family agents with local file and Python tools. The bundled script converts pixel-coordinate drafts into compact JSON with integer centered coordinates; it does not call an image-generation service.
Install the
skill folder
in your agent's skills
directory, then invoke
$moss-image-prompt-enhancer
with your image idea, desired
caption or Layout output, and any canvas dimensions. Paste the compiled result
into MOSS-Image's positive prompt; for Layout, use the same generation dimensions.
Layout-to-image generation
Pass a JSON layout as the prompt to describe the scene, rendered text, objects,
and their positions. Layouts use
summary.caption
and
items
, with
bbox_format: "yxyx"
and
bbox_coord_space: "abs_centralized"
.
With the Python API, serialize the layout using
json.dumps(layout, ensure_ascii=False)
and pass it to
pipe
. In Gradio, paste
the JSON into the Prompt field and set the matching image dimensions.
See the
layout format and example
.
Layouts can also support controlled editing and user-friendly layout tools. Edit text, element descriptions, and bounding boxes to adjust image content and composition in a structured way.
Showcase
Citation
@misc{mossimage2026,
title = {MOSS-Image},
author = {{OpenMOSS Team}},
year = {2026},
howpublished = {\url{https://github.com/OpenMOSS/MOSS-Image}}
}
License and acknowledgements
The model weights and bundled inference code are released under the Apache License, Version 2.0 .
We thank the Diffusers, Qwen, and FLUX teams.
Runs of OpenMOSS-Team MOSS-Image-SFT on huggingface.co
4.5K
Total runs
0
24-hour runs
2.3K
3-day runs
3.3K
7-day runs
3.3K
30-day runs
More Information About MOSS-Image-SFT huggingface.co Model
Url of MOSS-Image-SFT
MOSS-Image-SFT huggingface.co Url
Provider of MOSS-Image-SFT huggingface.co
Other API from OpenMOSS-Team
Updated:June 05 2026
Total runs:
195.9K
Run Growth:
28.9K
Growth Rate:
14.74%
Total runs:
158.0K
Run Growth:
-20.9K
Growth Rate:
-13.25%
Total runs:
100.2K
Run Growth:
71.1K
Growth Rate:
70.95%
Total runs:
88.4K
Run Growth:
49.9K
Growth Rate:
56.44%
Total runs:
65.1K
Run Growth:
-43.1K
Growth Rate:
-66.23%
Total runs:
22.8K
Run Growth:
8.8K
Growth Rate:
38.68%
Total runs:
21.4K
Run Growth:
-5.0K
Growth Rate:
-23.18%
Total runs:
14.2K
Run Growth:
-7.9K
Growth Rate:
-55.82%
Total runs:
13.6K
Run Growth:
4
Growth Rate:
0.03%
Total runs:
12.1K
Run Growth:
1.7K
Growth Rate:
13.86%
Total runs:
5.9K
Run Growth:
2.2K
Growth Rate:
36.72%
Total runs:
3.6K
Run Growth:
-1.0K
Growth Rate:
-29.16%
Total runs:
3.6K
Run Growth:
2.7K
Growth Rate:
97.37%
Total runs:
2.8K
Run Growth:
532
Growth Rate:
19.57%
Total runs:
2.6K
Run Growth:
1.1K
Growth Rate:
42.57%
Total runs:
2.1K
Run Growth:
395
Growth Rate:
18.48%
Total runs:
2.1K
Run Growth:
2.1K
Growth Rate:
98.47%
Total runs:
1.7K
Run Growth:
1.3K
Growth Rate:
78.25%
Total runs:
1.4K
Run Growth:
-2.7K
Growth Rate:
-198.75%
Total runs:
1.2K
Run Growth:
-259
Growth Rate:
-20.77%
Total runs:
1.1K
Run Growth:
-1.1K
Growth Rate:
-98.33%
Total runs:
764
Run Growth:
32
Growth Rate:
4.19%
Total runs:
625
Run Growth:
48
Growth Rate:
12.90%
Total runs:
592
Run Growth:
65
Growth Rate:
10.98%
Total runs:
552
Run Growth:
-195
Growth Rate:
-35.33%
Total runs:
534
Run Growth:
491
Growth Rate:
91.95%
Total runs:
437
Run Growth:
305
Growth Rate:
69.79%
Total runs:
343
Run Growth:
-751
Growth Rate:
-218.95%
Total runs:
207
Run Growth:
41
Growth Rate:
19.81%
Total runs:
150
Run Growth:
103
Growth Rate:
68.67%
Total runs:
148
Run Growth:
148
Growth Rate:
100.00%
Total runs:
144
Run Growth:
-504
Growth Rate:
-327.27%
Total runs:
119
Run Growth:
29
Growth Rate:
24.37%
Total runs:
115
Run Growth:
29
Growth Rate:
27.10%
Total runs:
114
Run Growth:
13
Growth Rate:
11.93%
Total runs:
111
Run Growth:
22
Growth Rate:
20.75%
Total runs:
105
Run Growth:
-38
Growth Rate:
-36.19%
Total runs:
93
Run Growth:
31
Growth Rate:
33.33%
Total runs:
89
Run Growth:
12
Growth Rate:
13.48%
Total runs:
59
Run Growth:
59
Growth Rate:
100.00%
Total runs:
55
Run Growth:
-109
Growth Rate:
-198.18%
Total runs:
53
Run Growth:
-30
Growth Rate:
-56.60%
Total runs:
48
Run Growth:
7
Growth Rate:
14.58%
Total runs:
46
Run Growth:
-7
Growth Rate:
-15.22%
Total runs:
46
Run Growth:
18
Growth Rate:
39.13%
Total runs:
44
Run Growth:
14
Growth Rate:
31.11%
Total runs:
42
Run Growth:
11
Growth Rate:
26.19%
Total runs:
32
Run Growth:
10
Growth Rate:
29.41%
Total runs:
31
Run Growth:
12
Growth Rate:
38.71%
Total runs:
26
Run Growth:
9
Growth Rate:
33.33%
Total runs:
26
Run Growth:
9
Growth Rate:
34.62%
Total runs:
24
Run Growth:
17
Growth Rate:
73.91%
Total runs:
23
Run Growth:
6
Growth Rate:
25.00%
Total runs:
22
Run Growth:
-6
Growth Rate:
-26.09%
Total runs:
22
Run Growth:
-1
Growth Rate:
-4.17%
Total runs:
22
Run Growth:
2
Growth Rate:
9.09%
Total runs:
21
Run Growth:
12
Growth Rate:
57.14%
Total runs:
21
Run Growth:
9
Growth Rate:
42.86%
Total runs:
20
Run Growth:
2
Growth Rate:
10.00%
Total runs:
19
Run Growth:
7
Growth Rate:
36.84%
Total runs:
19
Run Growth:
9
Growth Rate:
47.37%
Total runs:
19
Run Growth:
16
Growth Rate:
84.21%
Total runs:
18
Run Growth:
7
Growth Rate:
38.89%
Total runs:
17
Run Growth:
5
Growth Rate:
29.41%
Total runs:
16
Run Growth:
-1
Growth Rate:
-6.25%
Total runs:
16
Run Growth:
9
Growth Rate:
56.25%
Total runs:
15
Run Growth:
7
Growth Rate:
46.67%
Total runs:
15
Run Growth:
-31
Growth Rate:
-206.67%
Total runs:
14
Run Growth:
-13
Growth Rate:
-92.86%
Total runs:
14
Run Growth:
-1
Growth Rate:
-7.14%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
8
Growth Rate:
61.54%
Total runs:
13
Run Growth:
11
Growth Rate:
84.62%
Total runs:
12
Run Growth:
-15
Growth Rate:
-125.00%
Total runs:
11
Run Growth:
7
Growth Rate:
63.64%
Total runs:
11
Run Growth:
-3
Growth Rate:
-27.27%
Total runs:
11
Run Growth:
9
Growth Rate:
81.82%
Total runs:
10
Run Growth:
-24
Growth Rate:
-240.00%
Total runs:
10
Run Growth:
4
Growth Rate:
40.00%
Total runs:
10
Run Growth:
3
Growth Rate:
30.00%
Total runs:
10
Run Growth:
7
Growth Rate:
70.00%
Total runs:
9
Run Growth:
7
Growth Rate:
77.78%
Total runs:
9
Run Growth:
1
Growth Rate:
11.11%
Total runs:
9
Run Growth:
3
Growth Rate:
33.33%
Total runs:
9
Run Growth:
4
Growth Rate:
44.44%
Total runs:
9
Run Growth:
1
Growth Rate:
11.11%
Total runs:
8
Run Growth:
4
Growth Rate:
50.00%
Total runs:
8
Run Growth:
3
Growth Rate:
37.50%
Total runs:
8
Run Growth:
4
Growth Rate:
50.00%
Total runs:
8
Run Growth:
4
Growth Rate:
50.00%
Total runs:
7
Run Growth:
1
Growth Rate:
14.29%
Total runs:
7
Run Growth:
2
Growth Rate:
28.57%
Total runs:
7
Run Growth:
3
Growth Rate:
42.86%
Total runs:
7
Run Growth:
4
Growth Rate:
57.14%