Usa l'API RunComfy per eseguire kling/kling-3.0/pro/image-to-video. Per input e output accettati, consulta lo schema.
curl --request POST \
--url https://model-api.runcomfy.net/v1/models/kling/kling-3.0/pro/image-to-video \
--header "Content-Type: application/json" \
--header "Authorization: Bearer <token>" \
--data '{
"prompt": "Bring this still photograph to life with premium cinematic motion. The young American couple ride their two chestnut quarter horses side-by-side across the golden Montana plains at sunset — hooves rhythmically stepping forward, kicking up soft golden dust, horse manes and tails flowing in the prairie wind. The man in the cowboy hat and denim shirt glances over and laughs warmly; the woman in the cream cable-knit sweater laughs back, her wavy auburn hair whipping in the breeze. Tall amber prairie grass sways across the foreground in slow waves, distant Rocky Mountain silhouettes shimmer in heat haze, wispy pink-orange clouds drift slowly across the sky, a few birds wheel overhead. The camera follows in a smooth lateral tracking shot, parallax revealing the vastness of the open plains, then gently pushes in to a tighter two-shot of their faces. Natural ambient sound: rhythmic hoofbeats on dirt trail, leather creaking, wind through tall grass, distant meadowlark calls, and a soft acoustic country guitar score. Photoreal motion realism — every horse muscle flexing, hair strand moving, dust particle drifting, fabric folding — golden-hour rim lighting, lens flare, shot on Arri Alexa 35, 85mm anamorphic, shallow depth of field, premium cinematic color grade, Yellowstone-style.",
"start_image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7351/media-files/input.png"
}'Imposta la variabile d'ambiente YOUR_API_TOKEN con la tua chiave API (gestione nel Profilo) e includi in ogni richiesta un token Bearer nell'intestazione Authorization : Authorization: Bearer $YOUR_API_TOKEN.
Invia un job di generazione asincrono e ricevi subito un request_id e URL per stato, risultati e annullamento.
curl --request POST \
--url https://model-api.runcomfy.net/v1/models/kling/kling-3.0/pro/image-to-video \
--header "Content-Type: application/json" \
--header "Authorization: Bearer <token>" \
--data '{
"prompt": "Bring this still photograph to life with premium cinematic motion. The young American couple ride their two chestnut quarter horses side-by-side across the golden Montana plains at sunset — hooves rhythmically stepping forward, kicking up soft golden dust, horse manes and tails flowing in the prairie wind. The man in the cowboy hat and denim shirt glances over and laughs warmly; the woman in the cream cable-knit sweater laughs back, her wavy auburn hair whipping in the breeze. Tall amber prairie grass sways across the foreground in slow waves, distant Rocky Mountain silhouettes shimmer in heat haze, wispy pink-orange clouds drift slowly across the sky, a few birds wheel overhead. The camera follows in a smooth lateral tracking shot, parallax revealing the vastness of the open plains, then gently pushes in to a tighter two-shot of their faces. Natural ambient sound: rhythmic hoofbeats on dirt trail, leather creaking, wind through tall grass, distant meadowlark calls, and a soft acoustic country guitar score. Photoreal motion realism — every horse muscle flexing, hair strand moving, dust particle drifting, fabric folding — golden-hour rim lighting, lens flare, shot on Arri Alexa 35, 85mm anamorphic, shallow depth of field, premium cinematic color grade, Yellowstone-style.",
"start_image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7351/media-files/input.png"
}'Recupera lo stato corrente per un request_id ("in_queue", "in_progress", "completed" o "cancelled").
curl --request GET \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
--header "Authorization: Bearer <token>"Recupera output finali e metadati per il request_id; se il job non è completo, la risposta restituisce lo stato corrente per continuare il polling.
curl --request GET \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
--header "Authorization: Bearer <token>"Annulla un job in coda tramite request_id; i job in corso non possono essere annullati.
curl --request POST \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
--header "Authorization: Bearer <token>"Fornisci un URL HTTPS raggiungibile pubblicamente. L'host deve consentire fetch lato server (senza login/cookie), senza rate limit eccessivo o blocco bot. Consigliato: immagini ≤ 50 MB (~4K), video ≤ 100 MB (~2–5 min a 720p). Per asset privati, URL stabili o pre-firmati.
{
"type": "object",
"title": "Schema di input",
"required": [
"prompt",
"start_image_url"
],
"properties": {
"prompt": {
"title": "Prompt",
"description": "",
"type": "string",
"default": "Bring this still photograph to life with premium cinematic motion. The young American couple ride their two chestnut quarter horses side-by-side across the golden Montana plains at sunset — hooves rhythmically stepping forward, kicking up soft golden dust, horse manes and tails flowing in the prairie wind. The man in the cowboy hat and denim shirt glances over and laughs warmly; the woman in the cream cable-knit sweater laughs back, her wavy auburn hair whipping in the breeze. Tall amber prairie grass sways across the foreground in slow waves, distant Rocky Mountain silhouettes shimmer in heat haze, wispy pink-orange clouds drift slowly across the sky, a few birds wheel overhead. The camera follows in a smooth lateral tracking shot, parallax revealing the vastness of the open plains, then gently pushes in to a tighter two-shot of their faces. Natural ambient sound: rhythmic hoofbeats on dirt trail, leather creaking, wind through tall grass, distant meadowlark calls, and a soft acoustic country guitar score. Photoreal motion realism — every horse muscle flexing, hair strand moving, dust particle drifting, fabric folding — golden-hour rim lighting, lens flare, shot on Arri Alexa 35, 85mm anamorphic, shallow depth of field, premium cinematic color grade, Yellowstone-style."
},
"multi_prompt": {
"title": "Segmenti multiprompt",
"description": "Fornire più segmenti di prompt per le transizioni di scena. La somma delle durate di tutti i segmenti deve essere uguale alla durata totale del video.",
"type": "array",
"items": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"format": "str"
},
"duration": {
"type": "integer",
"format": "int_slider_with_range",
"minimum": 3,
"maximum": 15,
"default": 5
}
}
},
"maxItems": 20,
"minItems": 0
},
"start_image_url": {
"title": "Immagine iniziale",
"description": "Immagine iniziale del video. Supporta i formati jpg, jpeg, png, bmp, webp.",
"type": "string",
"default": "https://playgrounds-storage-public.runcomfy.net/tools/7351/media-files/input.png"
},
"end_image_url": {
"title": "Immagine finale",
"description": "Immagine finale opzionale per transizioni controllate tra due fotogrammi. Supporta i formati jpg, jpeg, png, bmp, webp.",
"type": "string"
},
"duration": {
"title": "Durata",
"description": "Durata totale del video generato in secondi.",
"type": "integer",
"minimum": 3,
"maximum": 15,
"default": 10
},
"generate_audio": {
"title": "Genera audio",
"description": "Abilita questa opzione per generare audio per il video.",
"type": "boolean",
"default": true
},
"elements": {
"title": "Elementi",
"description": "Risorse di input utilizzate per la generazione, incluse immagini di riferimento e segmenti video.",
"type": "array",
"items": {
"type": "object",
"properties": {
"frontal_image_url": {
"type": "string",
"format": "image_uri",
"description": "Riferimento all'immagine frontale del soggetto."
},
"reference_image_urls": {
"type": "array",
"format": "image_uris",
"items": {
"type": "string",
"format": "image_uri"
},
"description": "URL di immagini di riferimento aggiuntivi utilizzati per guidare il rendering."
},
"video_url": {
"type": "string",
"format": "video_uri",
"description": "Video sorgente opzionale utilizzato per riferimento al movimento."
}
}
},
"minItems": 0,
"maxItems": 3
},
"shot_type": {
"title": "Tipo di inquadratura",
"description": "Definisce come viene gestita la ripresa della telecamera o l'inquadratura della scena.",
"type": "string",
"enum": [
"customize"
],
"default": "customize"
},
"negative_prompt": {
"title": "Prompt negativo",
"description": "",
"type": "string"
},
"cfg_scale": {
"title": "Scala di guida",
"description": "Scala di guida senza classificatore che controlla l'aderenza al prompt.",
"type": "float",
"minimum": 0,
"maximum": 1,
"default": 0.5
}
}
}{
"output": {
"type": "object",
"properties": {
"image": {
"type": "string",
"format": "uri",
"description": "URL immagine singola"
},
"video": {
"type": "string",
"format": "uri",
"description": "URL video singolo"
},
"images": {
"type": "array",
"description": "più URL immagine",
"items": {
"type": "string",
"format": "uri"
}
},
"videos": {
"type": "array",
"description": "più URL video",
"items": {
"type": "string",
"format": "uri"
}
}
}
}
}RunComfy è la piattaforma principale ComfyUI che offre ComfyUI online ambiente e servizi, insieme a workflow di ComfyUI con visuali mozzafiato. RunComfy offre anche AI Models, consentire agli artisti di sfruttare gli ultimi strumenti di AI per creare arte incredibile.