{
 "1": {
  "class_type": "UNETLoader",
  "inputs": {
   "unet_name": "moss_image_sft_bf16.safetensors",
   "weight_dtype": "default"
  }
 },
 "30": {
  "class_type": "LoraLoaderModelOnly",
  "inputs": {
   "model": [
    "1",
    0
   ],
   "lora_name": "moss_image_sft_lora_blocks_21_to_49_rank_512_bf16.safetensors",
   "strength_model": -0.5
  }
 },
 "16": {
  "class_type": "TemporalScoreRescaling",
  "inputs": {
   "model": [
    "30",
    0
   ],
   "tsr_k": 0.95,
   "tsr_sigma": 1.0
  }
 },
 "2": {
  "class_type": "SkipLayerGuidanceDiTSimple",
  "inputs": {
   "model": [
    "16",
    0
   ],
   "double_layers": "",
   "single_layers": "22, 24",
   "start_percent": 0.1,
   "end_percent": 0.7
  }
 },
 "3": {
  "class_type": "CLIPLoader",
  "inputs": {
   "clip_name": "qwen3.5_9b_int8_convrot.safetensors",
   "type": "moss_image",
   "device": "default"
  }
 },
 "4": {
  "class_type": "VAELoader",
  "inputs": {
   "vae_name": "flux2-vae.safetensors"
  }
 },
 "18": {
  "class_type": "PrimitiveStringMultiline",
  "inputs": {
   "value": "You turn a user's image idea into one detailed caption for a text-to-image model. The model learned from captions that describe finished images, so write the caption as a description of the image itself, not as instructions.\n\nKeep the request\n- Keep everything the user specified: subjects, counts, actions, relationships, medium, style, mood, colors and anything they excluded. Never contradict or drop it.\n- Fill in what they left open with concrete visual choices: setting, composition and framing, viewpoint, lighting, materials and textures, color palette, and the artistic medium.\n- Describe only what can be seen. Leave out sounds, smells, backstory and intentions.\n- Do not invent real-world facts the user did not give, such as specific dates, prices, names or specifications.\n\nText in the image\n- Quote every piece of visible text exactly, in double quotes. Keep the user's wording, language, spelling, capitalization, punctuation and line breaks; never translate it.\n- If the user asks for a designed image (poster, cover, menu, label, sign, infographic) without giving its text, write short, specific copy that fits instead of placeholders.\n- Describe where each text sits and how it looks: position, reading order, alignment, line breaks, relative size, font style, color and spacing.\n- Do not mention watermarks or artist signatures.\n\nWriting\n- Write in English, in plain prose: one to three paragraphs, usually 80 to 200 words, longer only when there is a lot of text to place.\n- Open with the medium and the main subject, then the setting and composition, then lighting, colors and finer details.\n- Give positions with words such as left, right, top, bottom, foreground and background. No coordinates, lists, headings, JSON or Markdown.\n- No quality keywords such as \"masterpiece\", \"best quality\", \"8k\" or \"highly detailed\", and no negative prompt.\n\nReply with the caption only: no title, introduction, explanation or surrounding quotes.\n"
  }
 },
 "17": {
  "class_type": "TextGenerate",
  "inputs": {
   "clip": [
    "3",
    0
   ],
   "prompt": "",
   "max_length": 4096,
   "sampling_mode": "on",
   "sampling_mode.temperature": 0.7,
   "sampling_mode.top_k": 64,
   "sampling_mode.top_p": 0.95,
   "sampling_mode.min_p": 0.05,
   "sampling_mode.repetition_penalty": 1.05,
   "sampling_mode.seed": 0,
   "thinking": false,
   "use_default_template": true,
   "mtp": "auto",
   "system_prompt": [
    "18",
    0
   ]
  }
 },
 "19": {
  "class_type": "PreviewAny",
  "inputs": {
   "source": [
    "17",
    0
   ]
  }
 },
 "5": {
  "class_type": "CLIPTextEncode",
  "inputs": {
   "clip": [
    "3",
    0
   ],
   "text": [
    "17",
    0
   ]
  }
 },
 "6": {
  "class_type": "CLIPTextEncode",
  "inputs": {
   "clip": [
    "3",
    0
   ],
   "text": "worst quality, bad anatomy, watermark, jpeg artifact"
  }
 },
 "7": {
  "class_type": "EmptyFlux2LatentImage",
  "inputs": {
   "width": 1024,
   "height": 1024,
   "batch_size": 1
  }
 },
 "21": {
  "class_type": "SamplerER_SDE",
  "inputs": {
   "solver_type": "ER-SDE",
   "max_stage": 3,
   "eta": 1.0,
   "s_noise": 1.05
  }
 },
 "22": {
  "class_type": "BasicScheduler",
  "inputs": {
   "model": [
    "2",
    0
   ],
   "scheduler": "simple",
   "steps": 25,
   "denoise": 1.0
  }
 },
 "20": {
  "class_type": "SamplerCustom",
  "inputs": {
   "model": [
    "2",
    0
   ],
   "add_noise": true,
   "noise_seed": 16,
   "cfg": 3.0,
   "positive": [
    "5",
    0
   ],
   "negative": [
    "6",
    0
   ],
   "sampler": [
    "21",
    0
   ],
   "sigmas": [
    "22",
    0
   ],
   "latent_image": [
    "7",
    0
   ]
  }
 },
 "9": {
  "class_type": "VAEDecode",
  "inputs": {
   "samples": [
    "20",
    0
   ],
   "vae": [
    "4",
    0
   ]
  }
 },
 "10": {
  "class_type": "SaveImage",
  "inputs": {
   "images": [
    "9",
    0
   ],
   "filename_prefix": "moss/moss"
  }
 }
}