Instructions to use Comfy-Org/MOSS-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/MOSS-Image with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Simple-workflow.json
{
"id": "602a9b4a-8b28-4c64-a19e-fb35024af9c8",
"revision": 2,
"last_node_id": 38,
"last_link_id": 59,
"nodes": [
{
"id": 4,
"type": "CLIPTextEncode",
"pos": [
600,
280
],
"size": [
420,
230
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"localized_name": "clip",
"name": "clip",
"type": "CLIP",
"link": 54
},
{
"localized_name": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": null
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"slot_index": 0,
"links": [
18
]
}
],
"title": "moss-image Positive",
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.40.0"
},
"widgets_values": [
"Two plainclothes detectives in white shirts, one displaying a police badge while wearing sunglasses, interact with a blonde driver in a medium over-the-shoulder shot. The female driver grips the steering wheel in the foreground, while the two men lean outward from an adjacent vehicle toward the center frame. The grainy vintage film still features distant palm trees and architecture in the background under diffused natural daylight with soft shadows.\n"
],
"widgets_values_named": {
"text": "Two plainclothes detectives in white shirts, one displaying a police badge while wearing sunglasses, interact with a blonde driver in a medium over-the-shoulder shot. The female driver grips the steering wheel in the foreground, while the two men lean outward from an adjacent vehicle toward the center frame. The grainy vintage film still features distant palm trees and architecture in the background under diffused natural daylight with soft shadows.\n"
}
},
{
"id": 5,
"type": "CLIPTextEncode",
"pos": [
600,
550
],
"size": [
420,
150
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"localized_name": "clip",
"name": "clip",
"type": "CLIP",
"link": 55
},
{
"localized_name": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": null
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"slot_index": 0,
"links": [
19
]
}
],
"title": "moss-image Negative",
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.40.0"
},
"widgets_values": [
""
],
"widgets_values_named": {
"text": ""
}
},
{
"id": 6,
"type": "EmptyFlux2LatentImage",
"pos": [
300,
590
],
"size": [
270,
110
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "width",
"name": "width",
"type": "INT",
"widget": {
"name": "width"
},
"link": null
},
{
"localized_name": "height",
"name": "height",
"type": "INT",
"widget": {
"name": "height"
},
"link": null
},
{
"localized_name": "batch_size",
"name": "batch_size",
"type": "INT",
"widget": {
"name": "batch_size"
},
"link": null
}
],
"outputs": [
{
"localized_name": "LATENT",
"name": "LATENT",
"type": "LATENT",
"slot_index": 0,
"links": [
53
]
}
],
"properties": {
"Node name for S&R": "EmptyFlux2LatentImage",
"cnr_id": "comfy-core",
"ver": "0.40.0"
},
"widgets_values": [
2208,
1088,
1
],
"widgets_values_named": {
"width": 2208,
"height": 1088,
"batch_size": 1
}
},
{
"id": 17,
"type": "VAEDecode",
"pos": [
1190,
510
],
"size": [
140,
50
],
"flags": {
"collapsed": true
},
"order": 10,
"mode": 0,
"inputs": [
{
"localized_name": "samples",
"name": "samples",
"type": "LATENT",
"link": 22
},
{
"localized_name": "vae",
"name": "vae",
"type": "VAE",
"link": 46
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"slot_index": 0,
"links": [
21
]
}
],
"properties": {
"Node name for S&R": "VAEDecode",
"cnr_id": "comfy-core",
"ver": "0.40.0"
}
},
{
"id": 18,
"type": "SaveImage",
"pos": [
1350,
180
],
"size": [
480,
560
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"link": 21
},
{
"localized_name": "filename_prefix",
"name": "filename_prefix",
"type": "STRING",
"widget": {
"name": "filename_prefix"
},
"link": null
}
],
"outputs": [
{
"localized_name": "image_urls",
"name": "image_urls",
"type": "STRING",
"links": []
},
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.40.0",
"Node name for S&R": "SaveImage"
},
"widgets_values": [
"moss-image"
],
"widgets_values_named": {
"filename_prefix": "moss-image"
}
},
{
"id": 25,
"type": "VAELoader",
"pos": [
300,
440
],
"size": [
260,
60
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "vae_name",
"name": "vae_name",
"type": "COMBO",
"widget": {
"name": "vae_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "VAE",
"name": "VAE",
"type": "VAE",
"links": [
46
]
}
],
"properties": {
"Node name for S&R": "VAELoader",
"cnr_id": "comfy-core",
"ver": "0.40.0"
},
"widgets_values": [
"flux2-vae.safetensors"
],
"widgets_values_named": {
"vae_name": "flux2-vae.safetensors"
}
},
{
"id": 33,
"type": "SkipLayerGuidanceDiTSimple",
"pos": [
610,
180
],
"size": [
398.691015625,
130
],
"flags": {
"collapsed": true
},
"order": 8,
"mode": 0,
"showAdvanced": true,
"inputs": [
{
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 58
},
{
"localized_name": "double_layers",
"name": "double_layers",
"type": "STRING",
"widget": {
"name": "double_layers"
},
"link": null
},
{
"localized_name": "single_layers",
"name": "single_layers",
"type": "STRING",
"widget": {
"name": "single_layers"
},
"link": null
},
{
"localized_name": "start_percent",
"name": "start_percent",
"type": "FLOAT",
"widget": {
"name": "start_percent"
},
"link": null
},
{
"localized_name": "end_percent",
"name": "end_percent",
"type": "FLOAT",
"widget": {
"name": "end_percent"
},
"link": null
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
59
]
}
],
"title": "SkipLayerGuidanceDiTSimple (uncond skips block 22)",
"properties": {
"Node name for S&R": "SkipLayerGuidanceDiTSimple",
"cnr_id": "comfy-core",
"ver": "0.41.0"
},
"widgets_values": [
"",
"22",
0,
0.5
],
"widgets_values_named": {
"double_layers": "",
"single_layers": "22",
"start_percent": 0,
"end_percent": 0.5
}
},
{
"id": 31,
"type": "CLIPLoader",
"pos": [
290,
170
],
"size": [
270,
110
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "clip_name",
"name": "clip_name",
"type": "COMBO",
"widget": {
"name": "clip_name"
},
"link": null
},
{
"localized_name": "type",
"name": "type",
"type": "COMBO",
"widget": {
"name": "type"
},
"link": null
},
{
"localized_name": "device",
"name": "device",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "device"
},
"link": null
}
],
"outputs": [
{
"localized_name": "CLIP",
"name": "CLIP",
"type": "CLIP",
"slot_index": 0,
"links": [
54,
55
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader",
"cnr_id": "comfy-core",
"ver": "0.41.0"
},
"widgets_values": [
"qwen3.5_9b_int8_convrot.safetensors",
"moss_image",
"default"
],
"widgets_values_named": {
"clip_name": "qwen3.5_9b_int8_convrot.safetensors",
"type": "moss_image",
"device": "default"
}
},
{
"id": 32,
"type": "UNETLoader",
"pos": [
290,
320
],
"size": [
270,
90
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "unet_name",
"name": "unet_name",
"type": "COMBO",
"widget": {
"name": "unet_name"
},
"link": null
},
{
"localized_name": "weight_dtype",
"name": "weight_dtype",
"type": "COMBO",
"widget": {
"name": "weight_dtype"
},
"link": null
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
58
]
}
],
"properties": {
"Node name for S&R": "UNETLoader",
"cnr_id": "comfy-core",
"ver": "0.41.0"
},
"widgets_values": [
"moss_image_sft_int8_convrot.safetensors",
"default"
],
"widgets_values_named": {
"unet_name": "moss_image_sft_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
{
"id": 30,
"type": "Note",
"pos": [
-70,
140
],
"size": [
340,
350
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"MOSS-Image SFT \n\nCustom Node:\nhttps://github.com/OpenMOSS/MOSS-Image\nCopy "comfyui/moss-image" into "ComfyUI/custom_nodes/moss-image"\n(or search "MOSS-Image" in ComfyUI Manager once indexed).\n\nFile Placement:\n- Diffusion model: models/diffusion_models/moss_image_sft_int8_convrot.safetensors\n- Text encoder: models/text_encoders/qwen35_moss_int8_convrot.safetensors\n- VAE: models/vae/moss_flux2_small_vae.safetensors\n\nRecommended Settings:\n- Steps: 50\n- CFG: 3.0\n- Sampler: euler\n- Scheduler: sgm_uniform\n- Shift: 5.0 (ModelSamplingSD3)\n- Uncond skip: single_layers = 22\n- Resolution: 1024x1024 (multiples of 16)\n"
],
"widgets_values_named": {
"text": "MOSS-Image SFT \n\nCustom Node:\nhttps://github.com/OpenMOSS/MOSS-Image\nCopy "comfyui/moss-image" into "ComfyUI/custom_nodes/moss-image"\n(or search "MOSS-Image" in ComfyUI Manager once indexed).\n\nFile Placement:\n- Diffusion model: models/diffusion_models/moss_image_sft_int8_convrot.safetensors\n- Text encoder: models/text_encoders/qwen35_moss_int8_convrot.safetensors\n- VAE: models/vae/moss_flux2_small_vae.safetensors\n\nRecommended Settings:\n- Steps: 50\n- CFG: 3.0\n- Sampler: euler\n- Scheduler: sgm_uniform\n- Shift: 5.0 (ModelSamplingSD3)\n- Uncond skip: single_layers = 22\n- Resolution: 1024x1024 (multiples of 16)\n"
},
"color": "#223",
"bgcolor": "#335"
},
{
"id": 38,
"type": "Note",
"pos": [
-20.910235490232708,
611.0873909713091
],
"size": [
270.99496384297527,
99.07259579263723
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"https://t.me/yesocoai"
],
"widgets_values_named": {
"text": "https://t.me/yesocoai"
},
"color": "#223",
"bgcolor": "#335"
},
{
"id": 16,
"type": "KSampler",
"pos": [
1050,
190
],
"size": [
270,
270
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 59
},
{
"localized_name": "positive",
"name": "positive",
"type": "CONDITIONING",
"link": 18
},
{
"localized_name": "negative",
"name": "negative",
"type": "CONDITIONING",
"link": 19
},
{
"localized_name": "latent_image",
"name": "latent_image",
"type": "LATENT",
"link": 53
},
{
"localized_name": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": null
},
{
"localized_name": "steps",
"name": "steps",
"type": "INT",
"widget": {
"name": "steps"
},
"link": null
},
{
"localized_name": "cfg",
"name": "cfg",
"type": "FLOAT",
"widget": {
"name": "cfg"
},
"link": null
},
{
"localized_name": "sampler_name",
"name": "sampler_name",
"type": "COMBO",
"widget": {
"name": "sampler_name"
},
"link": null
},
{
"localized_name": "scheduler",
"name": "scheduler",
"type": "COMBO",
"widget": {
"name": "scheduler"
},
"link": null
},
{
"localized_name": "denoise",
"name": "denoise",
"type": "FLOAT",
"widget": {
"name": "denoise"
},
"link": null
}
],
"outputs": [
{
"localized_name": "LATENT",
"name": "LATENT",
"type": "LATENT",
"links": [
22
]
}
],
"properties": {
"Node name for S&R": "KSampler",
"cnr_id": "comfy-core",
"ver": "0.40.0"
},
"widgets_values": [
1,
"randomize",
50,
3,
"euler",
"simple",
1
],
"widgets_values_named": {
"seed": 1,
"control_after_generate": "randomize",
"steps": 50,
"cfg": 3,
"sampler_name": "euler",
"scheduler": "simple",
"denoise": 1
}
}
],
"links": [
[
18,
4,
0,
16,
1,
"CONDITIONING"
],
[
19,
5,
0,
16,
2,
"CONDITIONING"
],
[
21,
17,
0,
18,
0,
"IMAGE"
],
[
22,
16,
0,
17,
0,
"LATENT"
],
[
46,
25,
0,
17,
1,
"VAE"
],
[
53,
6,
0,
16,
3,
"LATENT"
],
[
54,
31,
0,
4,
0,
"CLIP"
],
[
55,
31,
0,
5,
0,
"CLIP"
],
[
58,
32,
0,
33,
0,
"MODEL"
],
[
59,
33,
0,
16,
0,
"MODEL"
]
],
"groups": [
{
"id": 1,
"title": "Model",
"bounding": [
280,
110,
300,
400
],
"flags": {}
},
{
"id": 2,
"title": "Group",
"bounding": [
590,
110,
440,
90
],
"flags": {}
},
{
"id": 3,
"title": "Prompt",
"bounding": [
590,
210,
440,
500
],
"flags": {}
},
{
"id": 5,
"title": "Image",
"bounding": [
1340,
110,
500,
650
],
"flags": {}
},
{
"id": 7,
"title": "Vae",
"bounding": [
290,
520,
290,
190
],
"flags": {}
},
{
"id": 9,
"title": "Ksampler",
"bounding": [
1040,
110,
290,
410
],
"flags": {}
}
],
"config": {},
"extra": {
"frontendVersion": "1.55.17",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true,
"ds": {
"scale": 1.185684210526316,
"offset": [
282.20361108013157,
56.38919977636653
]
}
},
"version": 0.4
}