{
  "id": "juggz-t2i-customer",
  "revision": 0,
  "last_node_id": 1111,
  "last_link_id": 12,
  "nodes": [
    {
      "id": 1001,
      "type": "Note",
      "pos": [
        80,
        340
      ],
      "size": [
        440,
        190
      ],
      "flags": {},
      "order": 0,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ① Load Model — Juggernaut Z",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "MODEL — Juggernaut Z\n\nLoads the Juggernaut Z model (fine-tune of the Z-Image base). On RunDiffusion it loads as a UNET/diffusion model, NOT a checkpoint.\n\nSelect: juggernautZ_v10ByRundiffusion.safetensors (public v1.0)."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 1,
      "type": "UNETLoader",
      "pos": [
        80,
        552
      ],
      "size": [
        440,
        110
      ],
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "MODEL",
          "type": "MODEL",
          "links": [
            3
          ],
          "slot_index": 0
        }
      ],
      "title": "① Load Model — Juggernaut Z",
      "properties": {
        "Node name for S&R": "UNETLoader"
      },
      "widgets_values": [
        "juggernautZ_v10ByRundiffusion.safetensors",
        "default"
      ]
    },
    {
      "id": 1002,
      "type": "Note",
      "pos": [
        80,
        782
      ],
      "size": [
        440,
        190
      ],
      "flags": {},
      "order": 2,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ② Load Text Encoder — Qwen3-4B",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "TEXT ENCODER — Qwen3-4B\n\nTurns your prompt into model guidance.\nIMPORTANT: 'type' MUST be 'qwen_image' for Z-Image / Juggernaut Z, or it won't load."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 2,
      "type": "CLIPLoader",
      "pos": [
        80,
        994
      ],
      "size": [
        440,
        130
      ],
      "flags": {},
      "order": 3,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "CLIP",
          "type": "CLIP",
          "links": [
            1,
            2
          ],
          "slot_index": 0
        }
      ],
      "title": "② Load Text Encoder — Qwen3-4B",
      "properties": {
        "Node name for S&R": "CLIPLoader"
      },
      "widgets_values": [
        "qwen_3_4b.safetensors",
        "qwen_image",
        "default"
      ]
    },
    {
      "id": 1003,
      "type": "Note",
      "pos": [
        80,
        1244
      ],
      "size": [
        440,
        190
      ],
      "flags": {},
      "order": 4,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ③ Load VAE — ae.safetensors",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "VAE — ae.safetensors\n\nDecodes the finished latent back into a viewable image."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 3,
      "type": "VAELoader",
      "pos": [
        80,
        1456
      ],
      "size": [
        440,
        90
      ],
      "flags": {},
      "order": 5,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "VAE",
          "type": "VAE",
          "links": [
            11
          ],
          "slot_index": 0
        }
      ],
      "title": "③ Load VAE — ae.safetensors",
      "properties": {
        "Node name for S&R": "VAELoader"
      },
      "widgets_values": [
        "ae.safetensors"
      ]
    },
    {
      "id": 1004,
      "type": "Note",
      "pos": [
        80,
        1666
      ],
      "size": [
        440,
        190
      ],
      "flags": {},
      "order": 6,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ④ Canvas Size (empty latent)",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "CANVAS SIZE (empty latent)\n\nText-to-image starts from a blank latent (pure noise) — no source image.\nSet width/height. Recommended Juggernaut Z sizes: 1024x1024, 832x1216 (portrait), 1216x832 (landscape).\nbatch_size = images per run."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 4,
      "type": "EmptySD3LatentImage",
      "pos": [
        80,
        1878
      ],
      "size": [
        440,
        130
      ],
      "flags": {},
      "order": 7,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "LATENT",
          "type": "LATENT",
          "links": [
            9
          ],
          "slot_index": 0
        }
      ],
      "title": "④ Canvas Size (empty latent)",
      "properties": {
        "Node name for S&R": "EmptySD3LatentImage"
      },
      "widgets_values": [
        1024,
        1024,
        1
      ]
    },
    {
      "id": 1006,
      "type": "Note",
      "pos": [
        620,
        340
      ],
      "size": [
        470,
        190
      ],
      "flags": {},
      "order": 8,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ⑤ Positive Prompt (what you WANT)",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "POSITIVE PROMPT\n\nDescribe what you WANT. Juggernaut Z rewards clear, visual, intentional prompts — pick the right words over piling on more."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 6,
      "type": "TextEncodeZImageOmni",
      "pos": [
        620,
        552
      ],
      "size": [
        470,
        280
      ],
      "flags": {},
      "order": 9,
      "mode": 0,
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 1
        }
      ],
      "outputs": [
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
          "links": [
            5
          ],
          "slot_index": 0
        }
      ],
      "title": "⑤ Positive Prompt (what you WANT)",
      "properties": {
        "Node name for S&R": "TextEncodeZImageOmni"
      },
      "widgets_values": [
        "a cinematic close-up portrait of a young woman with freckles and natural makeup, soft window light, shallow depth of field, ultra detailed skin texture, sharp focus, photorealistic",
        true
      ]
    },
    {
      "id": 1007,
      "type": "Note",
      "pos": [
        620,
        952
      ],
      "size": [
        470,
        190
      ],
      "flags": {},
      "order": 10,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ⑥ Negative Prompt (what you DON'T want)",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "NEGATIVE PROMPT\n\nDescribe what you DON'T want (blur, artifacts, extra fingers, etc.)."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 7,
      "type": "TextEncodeZImageOmni",
      "pos": [
        620,
        1164
      ],
      "size": [
        470,
        230
      ],
      "flags": {},
      "order": 11,
      "mode": 0,
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 2
        }
      ],
      "outputs": [
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
          "links": [
            6
          ],
          "slot_index": 0
        }
      ],
      "title": "⑥ Negative Prompt (what you DON'T want)",
      "properties": {
        "Node name for S&R": "TextEncodeZImageOmni"
      },
      "widgets_values": [
        "blurry, distorted, low resolution, deformed, extra fingers, jpeg artifacts, oversaturated",
        true
      ]
    },
    {
      "id": 1008,
      "type": "Note",
      "pos": [
        1180,
        340
      ],
      "size": [
        400,
        190
      ],
      "flags": {},
      "order": 12,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ⑦ Model Sampling (shift)",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "MODEL SAMPLING (shift)\n\nFlow-model sampling 'shift' for Z-Image. ~3.0 is a solid default. Higher = a touch more contrast/structure."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 8,
      "type": "ModelSamplingAuraFlow",
      "pos": [
        1180,
        552
      ],
      "size": [
        400,
        100
      ],
      "flags": {},
      "order": 13,
      "mode": 0,
      "inputs": [
        {
          "name": "model",
          "type": "MODEL",
          "link": 3
        }
      ],
      "outputs": [
        {
          "name": "MODEL",
          "type": "MODEL",
          "links": [
            4
          ],
          "slot_index": 0
        }
      ],
      "title": "⑦ Model Sampling (shift)",
      "properties": {
        "Node name for S&R": "ModelSamplingAuraFlow"
      },
      "widgets_values": [
        3.0
      ]
    },
    {
      "id": 1009,
      "type": "Note",
      "pos": [
        1180,
        772
      ],
      "size": [
        400,
        190
      ],
      "flags": {},
      "order": 14,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ⑧ Sampler — Juggernaut Z settings",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "SAMPLER — the engine\n\nRunDiffusion-recommended Juggernaut Z settings:\n  CFG 6 (range 6-9)\n  Steps 35 (range 25-45)\n  sampler res_multistep, scheduler beta\n\nDENOISE stays 1.00 for text-to-image (full generation from noise).\nSeed: set 'control_after_generate' to randomize for variety."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 9,
      "type": "KSampler",
      "pos": [
        1180,
        984
      ],
      "size": [
        400,
        300
      ],
      "flags": {},
      "order": 15,
      "mode": 0,
      "inputs": [
        {
          "name": "model",
          "type": "MODEL",
          "link": 4
        },
        {
          "name": "positive",
          "type": "CONDITIONING",
          "link": 5
        },
        {
          "name": "negative",
          "type": "CONDITIONING",
          "link": 6
        },
        {
          "name": "latent_image",
          "type": "LATENT",
          "link": 9
        }
      ],
      "outputs": [
        {
          "name": "LATENT",
          "type": "LATENT",
          "links": [
            10
          ],
          "slot_index": 0
        }
      ],
      "title": "⑧ Sampler — Juggernaut Z settings",
      "properties": {
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
        808520384108623,
        "randomize",
        35,
        6.0,
        "res_multistep",
        "beta",
        1.0
      ]
    },
    {
      "id": 1010,
      "type": "Note",
      "pos": [
        1640,
        340
      ],
      "size": [
        320,
        190
      ],
      "flags": {},
      "order": 16,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ⑨ Decode Latent → Image",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "DECODE LATENT → IMAGE\n\nConverts the finished latent into a normal image via the VAE."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 10,
      "type": "VAEDecode",
      "pos": [
        1640,
        552
      ],
      "size": [
        320,
        100
      ],
      "flags": {},
      "order": 17,
      "mode": 0,
      "inputs": [
        {
          "name": "samples",
          "type": "LATENT",
          "link": 10
        },
        {
          "name": "vae",
          "type": "VAE",
          "link": 11
        }
      ],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            12
          ],
          "slot_index": 0
        }
      ],
      "title": "⑨ Decode Latent → Image",
      "properties": {
        "Node name for S&R": "VAEDecode"
      },
      "widgets_values": []
    },
    {
      "id": 1011,
      "type": "Note",
      "pos": [
        1640,
        772
      ],
      "size": [
        480,
        190
      ],
      "flags": {},
      "order": 18,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "ℹ ⑩ Save Image",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "SAVE IMAGE\n\nWrites the final image to your outputs. Edit the filename prefix (e.g. MyProject/%date) to organize renders."
      ],
      "color": "#3a2a14",
      "bgcolor": "#5c4420"
    },
    {
      "id": 11,
      "type": "SaveImage",
      "pos": [
        1640,
        984
      ],
      "size": [
        480,
        470
      ],
      "flags": {},
      "order": 19,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 12
        }
      ],
      "outputs": [],
      "title": "⑩ Save Image",
      "properties": {
        "Node name for S&R": "SaveImage"
      },
      "widgets_values": [
        "JuggernautZ-Txt2Img"
      ]
    },
    {
      "id": 100,
      "type": "Note",
      "pos": [
        80,
        60
      ],
      "size": [
        1180,
        210
      ],
      "flags": {},
      "order": 20,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "★ README — read me first",
      "properties": {
        "text": ""
      },
      "widgets_values": [
        "JUGGERNAUT Z — TEXT TO IMAGE   (RunDiffusion · ComfyUI)\n\nGenerate an image from a text prompt. Follow the 4 colored steps left → right.\nEach node has a yellow ℹ note above it explaining what it does.\n\nQUICK START:  ① pick the model  ·  ④ set size  ·  ⑤/⑥ write prompts  ·  press Queue Prompt\nRecommended (RunDiffusion): CFG 6, 35 steps, res_multistep + beta, denoise 1.0."
      ],
      "color": "#1d3a52",
      "bgcolor": "#0f2436"
    }
  ],
  "links": [
    [
      1,
      2,
      0,
      6,
      0,
      "CLIP"
    ],
    [
      2,
      2,
      0,
      7,
      0,
      "CLIP"
    ],
    [
      3,
      1,
      0,
      8,
      0,
      "MODEL"
    ],
    [
      4,
      8,
      0,
      9,
      0,
      "MODEL"
    ],
    [
      5,
      6,
      0,
      9,
      1,
      "CONDITIONING"
    ],
    [
      6,
      7,
      0,
      9,
      2,
      "CONDITIONING"
    ],
    [
      9,
      4,
      0,
      9,
      3,
      "LATENT"
    ],
    [
      10,
      9,
      0,
      10,
      0,
      "LATENT"
    ],
    [
      11,
      3,
      0,
      10,
      1,
      "VAE"
    ],
    [
      12,
      10,
      0,
      11,
      0,
      "IMAGE"
    ]
  ],
  "groups": [
    {
      "id": 1,
      "title": "STEP 1 · MODELS & INPUTS",
      "bounding": [
        52,
        282,
        496,
        1754
      ],
      "color": "#2e4a62",
      "font_size": 22,
      "flags": {}
    },
    {
      "id": 2,
      "title": "STEP 2 · PROMPTS",
      "bounding": [
        592,
        282,
        526,
        1140
      ],
      "color": "#2e6246",
      "font_size": 22,
      "flags": {}
    },
    {
      "id": 3,
      "title": "STEP 3 · GENERATION",
      "bounding": [
        1152,
        282,
        456,
        1030
      ],
      "color": "#5a3a62",
      "font_size": 22,
      "flags": {}
    },
    {
      "id": 4,
      "title": "STEP 4 · OUTPUT",
      "bounding": [
        1612,
        282,
        536,
        1200
      ],
      "color": "#62402e",
      "font_size": 22,
      "flags": {}
    }
  ],
  "config": {},
  "extra": {
    "ds": {
      "scale": 0.5,
      "offset": [
        40,
        20
      ]
    }
  },
  "version": 0.4
}