smartbotic/nodes/sdcpp/sdcpp-model-load.js

/**
 * @node sdcpp-model-load
 * @name SD.cpp Load Model
 * @category sdcpp
 * @version 1.0.0
 * @description Make sure a model is loaded, without reloading one that already is
 * @icon box
 */

const configSchema = {
    type: 'object',
    properties: {
        serverUrl: {
            type: 'string', title: 'Server URL',
            description: 'Base address of the sdcpp-restapi server',
            default: 'http://localhost:8077'
        },
        credentialId: {
            type: 'string', title: 'Credential',
            description: 'A basic credential holding the sdcpp-restapi username and password',
            dynamicOptions: { source: 'credentials', filter: { type: ['basic'] } }
        },
        modelName: {
            type: 'string', title: 'Model',
            description: 'File name of the model, relative to its type directory. Usually supplied by an SD.cpp Model node rather than typed here'
        },
        modelType: {
            type: 'string', title: 'Model Type',
            enum: ['', 'checkpoint', 'diffusion'],
            default: '',
            description: 'checkpoint bundles U-Net, CLIP and VAE and suits SD1, SD2 and SDXL. diffusion holds only the U-Net or DiT and needs its components named separately, which is how Flux, SD3, Qwen, Wan and Z-Image load'
        },
        vae: { type: 'string', title: 'VAE', description: 'Component file name' },
        clipL: { type: 'string', title: 'CLIP-L', description: 'Component file name' },
        clipG: { type: 'string', title: 'CLIP-G', description: 'Component file name' },
        t5xxl: { type: 'string', title: 'T5-XXL', description: 'Component file name' },
        llm: { type: 'string', title: 'LLM', description: 'Component file name, used by Z-Image, Qwen, Anima and Flux2' },
        taesd: { type: 'string', title: 'TAESD', description: 'Tiny autoencoder for progress previews' },
        controlnet: { type: 'string', title: 'ControlNet', description: 'Component file name' },
        options: {
            type: 'object', title: 'Load Options',
            description: 'Extra load options passed through, such as flash_attn, enable_mmap, weight_type, stream_layers or max_vram'
        },
        whenDifferent: {
            type: 'string', title: 'When A Different Model Is Loaded',
            enum: ['load', 'fail'],
            default: 'load',
            description: 'load swaps it. fail stops the run instead - for a workflow that depends on a particular model already being in place and should not quietly spend minutes swapping it'
        },
        force: {
            type: 'boolean', title: 'Force Reload',
            default: false,
            description: 'Load again even when the right model is already loaded. Costs the full load time; useful after changing components or options, which this node cannot see from outside',
            showWhen: { field: 'whenDifferent', value: 'load' }
        },
        timeout: {
            type: 'number', title: 'Timeout (ms)',
            description: 'Loading reads gigabytes from disk and can take minutes',
            default: 300000
        }
    },
    required: []
};

const inputSchema = { type: 'object', properties: { data: { type: 'any' } } };

const outputSchema = {
    type: 'object',
    properties: {
        modelName: { type: 'string', description: 'The model that is loaded now' },
        modelType: { type: 'string' },
        architecture: { type: 'string', description: 'Architecture the server detected, which decides generation defaults' },
        loaded: { type: 'boolean', description: 'True when this node performed a load' },
        alreadyLoaded: { type: 'boolean', description: 'True when the right model was already in place and nothing was done' },
        previousModel: { type: 'string', description: 'What was loaded before, when this node swapped it' },
        loadedComponents: { type: 'object' },
        elapsedMs: { type: 'number' }
    }
};

function normalizeServer(url) {
    const value = String(url || '').trim();
    if (!value) {
        throw new Error('SD.cpp: a server URL is required, such as http://localhost:8077');
    }
    return value.replace(/\/+$/, '');
}

function readCredential(credentialId) {
    const auth = smartbotic.credentials.get(credentialId);
    if (!auth || auth.success !== true) {
        throw new Error('SD.cpp: could not read the credential: ' +
            ((auth && auth.error) || 'unknown error'));
    }

    const value = auth.headerValue || '';
    if (value.indexOf('Basic ') !== 0) {
        throw new Error('SD.cpp: the credential must be a basic one, holding the sdcpp-restapi ' +
            'username and password');
    }

    const decoded = smartbotic.utils.base64Decode(value.substring(6));
    const separator = decoded.indexOf(':');
    if (separator < 1) {
        throw new Error('SD.cpp: the credential is malformed, expected a username and a password');
    }

    return {
        username: decoded.substring(0, separator),
        password: decoded.substring(separator + 1)
    };
}

function call(options) {
    const response = smartbotic.http.request(options);

    let body = response.data;
    if (typeof body === 'string' && body.length > 0) {
        try {
            body = JSON.parse(body);
        } catch (e) {
            const snippet = body.substring(0, 200).replace(/\s+/g, ' ');
            throw new Error('SD.cpp: ' + options.what + ' returned HTTP ' + response.status +
                ' with a body that is not JSON: ' + snippet);
        }
    }

    if (response.status < 200 || response.status >= 300) {
        const detail = (body && (body.message || body.error)) || ('HTTP ' + response.status);
        throw new Error('SD.cpp: ' + options.what + ' failed: ' + detail);
    }

    return body || {};
}

function login(server, credential, timeout) {
    const session = call({
        method: 'POST',
        url: server + '/auth/login',
        headers: { 'Content-Type': 'application/json' },
        body: JSON.stringify({
            username: credential.username,
            password: credential.password
        }),
        timeout: timeout,
        what: 'signing in'
    });

    if (!session.token) {
        throw new Error('SD.cpp: the server accepted the login but returned no token');
    }
    return session.token;
}

// /health is unauthenticated, and it is the only way to find out what is
// already loaded without asking for a token first.
function readHealth(server, timeout) {
    return call({
        method: 'GET',
        url: server + '/health',
        timeout: timeout,
        what: 'reading server health'
    });
}

function putIfSet(target, key, value) {
    if (value === undefined || value === null || value === '') {
        return;
    }
    target[key] = value;
}

async function execute(config, input, context) {
    const server = normalizeServer(config.serverUrl);
    const timeout = config.timeout > 0 ? config.timeout : 300000;
    const modelName = String(config.modelName || '').trim();

    if (!modelName) {
        throw new Error('SD.cpp: a model name is required. Connect an SD.cpp Model node, ' +
            'or type the file name');
    }

    // Ask what is loaded before loading anything. A load takes minutes and
    // unloads whatever was there, so doing it when the right model is already
    // resident is pure cost - and on a shared server it disrupts other work.
    const startedAt = Date.now();
    const health = readHealth(server, Math.min(timeout, 15000));
    const current = health.model_name || '';
    const sameModel = current === modelName;

    if (sameModel && config.force !== true) {
        smartbotic.log.info('SD.cpp: ' + modelName + ' is already loaded, nothing to do');
        return {
            modelName: current,
            modelType: health.model_type || '',
            architecture: health.model_architecture || '',
            loaded: false,
            alreadyLoaded: true,
            previousModel: '',
            loadedComponents: health.loaded_components || {},
            elapsedMs: Date.now() - startedAt
        };
    }

    if (!sameModel && (config.whenDifferent || 'load') === 'fail') {
        throw new Error('SD.cpp: this workflow expects "' + modelName + '" to be loaded, but ' +
            (current ? 'the server has "' + current + '"' : 'no model is loaded') +
            '. Set When A Different Model Is Loaded to "load" to swap it automatically');
    }

    const credential = readCredential(config.credentialId);
    const token = login(server, credential, Math.min(timeout, 30000));

    const body = { model_name: modelName };
    putIfSet(body, 'model_type', config.modelType);
    putIfSet(body, 'vae', config.vae);
    putIfSet(body, 'clip_l', config.clipL);
    putIfSet(body, 'clip_g', config.clipG);
    putIfSet(body, 't5xxl', config.t5xxl);
    putIfSet(body, 'llm', config.llm);
    putIfSet(body, 'taesd', config.taesd);
    putIfSet(body, 'controlnet', config.controlnet);
    if (config.options && typeof config.options === 'object') {
        body.options = config.options;
    }

    smartbotic.log.info('SD.cpp: loading ' + modelName +
        (current ? ' (replacing ' + current + ')' : ''));

    // Loading unloads whatever was in the slot first, and the server holds a
    // mutex for the duration, so this blocks until the weights are resident.
    const loaded = call({
        method: 'POST',
        url: server + '/models/load',
        headers: { 'Content-Type': 'application/json', 'Authorization': 'Bearer ' + token },
        body: JSON.stringify(body),
        timeout: timeout,
        what: 'loading model ' + modelName
    });

    const after = readHealth(server, Math.min(timeout, 15000));

    return {
        modelName: loaded.model_name || modelName,
        modelType: loaded.model_type || config.modelType || '',
        architecture: after.model_architecture || '',
        loaded: true,
        alreadyLoaded: false,
        previousModel: sameModel ? '' : current,
        loadedComponents: loaded.loaded_components || after.loaded_components || {},
        elapsedMs: Date.now() - startedAt
    };
}

module.exports = { configSchema, inputSchema, outputSchema, execute };