Aurora v1
Aurora v1 is a multimodal avatar video generation model that creates talking-head videos from a single image and an audio input. It focuses on realistic facial animation, accurate lip synchronization, and expressive motion, producing studio-quality results for spoken or musical performances.
Weathered Lighthouse Keeper Monologue
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'creatify:aurora@0',
positivePrompt: 'A grounded cinematic talking-head performance of a seasoned lighthouse keeper speaking thoughtfully to camera, subtle expressive motion, natural blinking, gentle head turns, convincing mouth shapes, realistic skin texture, soft coastal daylight, restrained emotional delivery, studio-quality facial animation, highly believable lip synchronization',
CFGScale: 1,
inputs: {
image: 'https://assets.runware.ai/assets/inputs/ba308044-38c8-47df-86fd-ac43b3e1aae8.jpg',
audio: 'https://assets.runware.ai/assets/inputs/13797275-8403-428a-b277-15aff0bc6f36.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "creatify:aurora@0",
"positivePrompt": "A grounded cinematic talking-head performance of a seasoned lighthouse keeper speaking thoughtfully to camera, subtle expressive motion, natural blinking, gentle head turns, convincing mouth shapes, realistic skin texture, soft coastal daylight, restrained emotional delivery, studio-quality facial animation, highly believable lip synchronization",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/ba308044-38c8-47df-86fd-ac43b3e1aae8.jpg",
"audio": "https://assets.runware.ai/assets/inputs/13797275-8403-428a-b277-15aff0bc6f36.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "videoInference",
"taskUUID": "67613ddc-2405-42bb-be8b-9714e84e63aa",
"model": "creatify:aurora@0",
"positivePrompt": "A grounded cinematic talking-head performance of a seasoned lighthouse keeper speaking thoughtfully to camera, subtle expressive motion, natural blinking, gentle head turns, convincing mouth shapes, realistic skin texture, soft coastal daylight, restrained emotional delivery, studio-quality facial animation, highly believable lip synchronization",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/ba308044-38c8-47df-86fd-ac43b3e1aae8.jpg",
"audio": "https://assets.runware.ai/assets/inputs/13797275-8403-428a-b277-15aff0bc6f36.mp3"
}
}
]'runware run creatify:aurora@0 \
positivePrompt="A grounded cinematic talking-head performance of a seasoned lighthouse keeper speaking thoughtfully to camera, subtle expressive motion, natural blinking, gentle head turns, convincing mouth shapes, realistic skin texture, soft coastal daylight, restrained emotional delivery, studio-quality facial animation, highly believable lip synchronization" \
CFGScale=1 \
inputs.image=https://assets.runware.ai/assets/inputs/ba308044-38c8-47df-86fd-ac43b3e1aae8.jpg \
inputs.audio=https://assets.runware.ai/assets/inputs/13797275-8403-428a-b277-15aff0bc6f36.mp3{
"taskType": "videoInference",
"taskUUID": "67613ddc-2405-42bb-be8b-9714e84e63aa",
"model": "creatify:aurora@0",
"positivePrompt": "A grounded cinematic talking-head performance of a seasoned lighthouse keeper speaking thoughtfully to camera, subtle expressive motion, natural blinking, gentle head turns, convincing mouth shapes, realistic skin texture, soft coastal daylight, restrained emotional delivery, studio-quality facial animation, highly believable lip synchronization",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/ba308044-38c8-47df-86fd-ac43b3e1aae8.jpg",
"audio": "https://assets.runware.ai/assets/inputs/13797275-8403-428a-b277-15aff0bc6f36.mp3"
}
}{
"taskType": "videoInference",
"taskUUID": "67613ddc-2405-42bb-be8b-9714e84e63aa",
"videoUUID": "f041a335-f6db-4dcd-af1c-3f429763319a",
"videoURL": "https://vm.runware.ai/video/os/a20d05/ws/5/vi/f041a335-f6db-4dcd-af1c-3f429763319a.mp4",
"cost": 1.82
}Velvet Cabaret Singer Closeup
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'creatify:aurora@0',
positivePrompt: 'Studio-quality talking-head performance of an expressive jazz singer in a warm cabaret setting, accurate mouth shapes matching the vocal track, subtle head sway, natural blinking, emotive eyes, gentle shoulder movement, believable breathing, refined facial muscle motion, realistic skin texture, soft amber key light, rich crimson background, polished cinematic look',
CFGScale: 1,
inputs: {
image: 'https://assets.runware.ai/assets/inputs/079e83ee-5140-47c1-abce-db2455bdad2e.jpg',
audio: 'https://assets.runware.ai/assets/inputs/1e37071b-5f68-4154-a366-65a93bbbb508.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "creatify:aurora@0",
"positivePrompt": "Studio-quality talking-head performance of an expressive jazz singer in a warm cabaret setting, accurate mouth shapes matching the vocal track, subtle head sway, natural blinking, emotive eyes, gentle shoulder movement, believable breathing, refined facial muscle motion, realistic skin texture, soft amber key light, rich crimson background, polished cinematic look",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/079e83ee-5140-47c1-abce-db2455bdad2e.jpg",
"audio": "https://assets.runware.ai/assets/inputs/1e37071b-5f68-4154-a366-65a93bbbb508.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "videoInference",
"taskUUID": "1a24e3e0-67bb-4a7f-8639-34d1dc0add0b",
"model": "creatify:aurora@0",
"positivePrompt": "Studio-quality talking-head performance of an expressive jazz singer in a warm cabaret setting, accurate mouth shapes matching the vocal track, subtle head sway, natural blinking, emotive eyes, gentle shoulder movement, believable breathing, refined facial muscle motion, realistic skin texture, soft amber key light, rich crimson background, polished cinematic look",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/079e83ee-5140-47c1-abce-db2455bdad2e.jpg",
"audio": "https://assets.runware.ai/assets/inputs/1e37071b-5f68-4154-a366-65a93bbbb508.mp3"
}
}
]'runware run creatify:aurora@0 \
positivePrompt="Studio-quality talking-head performance of an expressive jazz singer in a warm cabaret setting, accurate mouth shapes matching the vocal track, subtle head sway, natural blinking, emotive eyes, gentle shoulder movement, believable breathing, refined facial muscle motion, realistic skin texture, soft amber key light, rich crimson background, polished cinematic look" \
CFGScale=1 \
inputs.image=https://assets.runware.ai/assets/inputs/079e83ee-5140-47c1-abce-db2455bdad2e.jpg \
inputs.audio=https://assets.runware.ai/assets/inputs/1e37071b-5f68-4154-a366-65a93bbbb508.mp3{
"taskType": "videoInference",
"taskUUID": "1a24e3e0-67bb-4a7f-8639-34d1dc0add0b",
"model": "creatify:aurora@0",
"positivePrompt": "Studio-quality talking-head performance of an expressive jazz singer in a warm cabaret setting, accurate mouth shapes matching the vocal track, subtle head sway, natural blinking, emotive eyes, gentle shoulder movement, believable breathing, refined facial muscle motion, realistic skin texture, soft amber key light, rich crimson background, polished cinematic look",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/079e83ee-5140-47c1-abce-db2455bdad2e.jpg",
"audio": "https://assets.runware.ai/assets/inputs/1e37071b-5f68-4154-a366-65a93bbbb508.mp3"
}
}{
"taskType": "videoInference",
"taskUUID": "1a24e3e0-67bb-4a7f-8639-34d1dc0add0b",
"videoUUID": "280af5c4-9220-4437-9df6-25f6e8a4f6b8",
"videoURL": "https://vm.runware.ai/video/os/a08d21/ws/5/vi/280af5c4-9220-4437-9df6-25f6e8a4f6b8.mp4",
"cost": 1.4
}Velvet Cabaret Vocalist Closeup
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'creatify:aurora@0',
positivePrompt: 'A realistic studio-quality performance video of an elegant cabaret singer delivering a soulful jazz vocal into a classic microphone, warm theatrical lighting, rich velvet drapery behind her, expressive eyes, natural breathing, delicate shoulder movement, refined hand gestures near the microphone, accurate mouth shapes for sung vowels and consonants, subtle emotional shifts across phrases, polished cinematography, believable skin detail, graceful head turns, immersive stage presence',
CFGScale: 1,
inputs: {
image: 'https://assets.runware.ai/assets/inputs/42a0c05d-b10c-4a9b-b201-0e6413bcd28a.jpg',
audio: 'https://assets.runware.ai/assets/inputs/4f30a746-eb81-44fd-8457-4cc6d94571f6.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "creatify:aurora@0",
"positivePrompt": "A realistic studio-quality performance video of an elegant cabaret singer delivering a soulful jazz vocal into a classic microphone, warm theatrical lighting, rich velvet drapery behind her, expressive eyes, natural breathing, delicate shoulder movement, refined hand gestures near the microphone, accurate mouth shapes for sung vowels and consonants, subtle emotional shifts across phrases, polished cinematography, believable skin detail, graceful head turns, immersive stage presence",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/42a0c05d-b10c-4a9b-b201-0e6413bcd28a.jpg",
"audio": "https://assets.runware.ai/assets/inputs/4f30a746-eb81-44fd-8457-4cc6d94571f6.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "videoInference",
"taskUUID": "568019a0-82cd-45be-aa1c-46e3d0bba9b1",
"model": "creatify:aurora@0",
"positivePrompt": "A realistic studio-quality performance video of an elegant cabaret singer delivering a soulful jazz vocal into a classic microphone, warm theatrical lighting, rich velvet drapery behind her, expressive eyes, natural breathing, delicate shoulder movement, refined hand gestures near the microphone, accurate mouth shapes for sung vowels and consonants, subtle emotional shifts across phrases, polished cinematography, believable skin detail, graceful head turns, immersive stage presence",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/42a0c05d-b10c-4a9b-b201-0e6413bcd28a.jpg",
"audio": "https://assets.runware.ai/assets/inputs/4f30a746-eb81-44fd-8457-4cc6d94571f6.mp3"
}
}
]'runware run creatify:aurora@0 \
positivePrompt="A realistic studio-quality performance video of an elegant cabaret singer delivering a soulful jazz vocal into a classic microphone, warm theatrical lighting, rich velvet drapery behind her, expressive eyes, natural breathing, delicate shoulder movement, refined hand gestures near the microphone, accurate mouth shapes for sung vowels and consonants, subtle emotional shifts across phrases, polished cinematography, believable skin detail, graceful head turns, immersive stage presence" \
CFGScale=1 \
inputs.image=https://assets.runware.ai/assets/inputs/42a0c05d-b10c-4a9b-b201-0e6413bcd28a.jpg \
inputs.audio=https://assets.runware.ai/assets/inputs/4f30a746-eb81-44fd-8457-4cc6d94571f6.mp3{
"taskType": "videoInference",
"taskUUID": "568019a0-82cd-45be-aa1c-46e3d0bba9b1",
"model": "creatify:aurora@0",
"positivePrompt": "A realistic studio-quality performance video of an elegant cabaret singer delivering a soulful jazz vocal into a classic microphone, warm theatrical lighting, rich velvet drapery behind her, expressive eyes, natural breathing, delicate shoulder movement, refined hand gestures near the microphone, accurate mouth shapes for sung vowels and consonants, subtle emotional shifts across phrases, polished cinematography, believable skin detail, graceful head turns, immersive stage presence",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/42a0c05d-b10c-4a9b-b201-0e6413bcd28a.jpg",
"audio": "https://assets.runware.ai/assets/inputs/4f30a746-eb81-44fd-8457-4cc6d94571f6.mp3"
}
}{
"taskType": "videoInference",
"taskUUID": "568019a0-82cd-45be-aa1c-46e3d0bba9b1",
"videoUUID": "5a309bc4-88cc-47dc-957c-502cd77797e6",
"videoURL": "https://vm.runware.ai/video/os/a25d05/ws/5/vi/5a309bc4-88cc-47dc-957c-502cd77797e6.mp4",
"cost": 1.54
}Velvet-Curtained Cabaret Vocalist
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'creatify:aurora@0',
positivePrompt: 'A polished talking-head performance video of a charismatic cabaret vocalist framed from the waist up, singing into a classic microphone with nuanced facial expressions, precise mouth movements, subtle head sway, confident eye focus, warm theatrical spotlight, rich crimson curtain backdrop, realistic skin texture, natural motion, cinematic stage ambiance',
CFGScale: 1,
inputs: {
image: 'https://assets.runware.ai/assets/inputs/66f602e1-1531-40ed-84c6-c2d131a91a3c.jpg',
audio: 'https://assets.runware.ai/assets/inputs/53c5739f-98ef-444b-b49b-5205177d843d.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "creatify:aurora@0",
"positivePrompt": "A polished talking-head performance video of a charismatic cabaret vocalist framed from the waist up, singing into a classic microphone with nuanced facial expressions, precise mouth movements, subtle head sway, confident eye focus, warm theatrical spotlight, rich crimson curtain backdrop, realistic skin texture, natural motion, cinematic stage ambiance",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/66f602e1-1531-40ed-84c6-c2d131a91a3c.jpg",
"audio": "https://assets.runware.ai/assets/inputs/53c5739f-98ef-444b-b49b-5205177d843d.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "videoInference",
"taskUUID": "9b4261db-3c7d-4fa2-9dfd-7a6fadb01a7f",
"model": "creatify:aurora@0",
"positivePrompt": "A polished talking-head performance video of a charismatic cabaret vocalist framed from the waist up, singing into a classic microphone with nuanced facial expressions, precise mouth movements, subtle head sway, confident eye focus, warm theatrical spotlight, rich crimson curtain backdrop, realistic skin texture, natural motion, cinematic stage ambiance",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/66f602e1-1531-40ed-84c6-c2d131a91a3c.jpg",
"audio": "https://assets.runware.ai/assets/inputs/53c5739f-98ef-444b-b49b-5205177d843d.mp3"
}
}
]'runware run creatify:aurora@0 \
positivePrompt="A polished talking-head performance video of a charismatic cabaret vocalist framed from the waist up, singing into a classic microphone with nuanced facial expressions, precise mouth movements, subtle head sway, confident eye focus, warm theatrical spotlight, rich crimson curtain backdrop, realistic skin texture, natural motion, cinematic stage ambiance" \
CFGScale=1 \
inputs.image=https://assets.runware.ai/assets/inputs/66f602e1-1531-40ed-84c6-c2d131a91a3c.jpg \
inputs.audio=https://assets.runware.ai/assets/inputs/53c5739f-98ef-444b-b49b-5205177d843d.mp3{
"taskType": "videoInference",
"taskUUID": "9b4261db-3c7d-4fa2-9dfd-7a6fadb01a7f",
"model": "creatify:aurora@0",
"positivePrompt": "A polished talking-head performance video of a charismatic cabaret vocalist framed from the waist up, singing into a classic microphone with nuanced facial expressions, precise mouth movements, subtle head sway, confident eye focus, warm theatrical spotlight, rich crimson curtain backdrop, realistic skin texture, natural motion, cinematic stage ambiance",
"CFGScale": 1,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/66f602e1-1531-40ed-84c6-c2d131a91a3c.jpg",
"audio": "https://assets.runware.ai/assets/inputs/53c5739f-98ef-444b-b49b-5205177d843d.mp3"
}
}{
"taskType": "videoInference",
"taskUUID": "9b4261db-3c7d-4fa2-9dfd-7a6fadb01a7f",
"videoUUID": "54efc27f-1074-409a-b453-6990f9dc6237",
"videoURL": "https://vm.runware.ai/video/os/a25d05/ws/5/vi/54efc27f-1074-409a-b453-6990f9dc6237.mp4",
"cost": 1.54
}