Seedream 4.5 Edit

doubao/seedream-4.5/image-to-image

doubao/seedream-4.5/image-to-image. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

Modelli correlati

Seedream 4.5 Edit Modelli correlati 1

Parametri completi, schema di output e prezzi aggiornati

Marketplace delle API per modelli IAUna piattaforma per tuttoPiù popolareTerminiEsplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.
images *Imagesimage_upload—image/* · 1–10 items
prompt *Prompttextarea—≤ 5000 chars
sizeSizeselect2K2K | 4K
aspect_ratioAspect Ratioselect1:11:1 | 3:2 | 2:3 | 3:4 | 4:3 | 9:16 | 16:9 | 21:9

Parametri completi, schema di output e prezzi aggiornati

Scopri di piùUna piattaforma per tuttoEsplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.
imagesarray<string>

API

Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.5/image-to-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "images": [
      "https://assets-public.namifusion.com/uploads/images/2026-04-21/76c1186af77d.png",
      "https://assets-public.namifusion.com/uploads/images/2026-04-21/149467630166.png"
    ],
    "prompt": "Enhance the facial features while preserving natural skin tone and texture. Add soft lighting and a cinematic color grade.",
    "size": "4K",
    "aspect_ratio": "16:9"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.5/image-to-image",
    headers=HEADERS,
    json={
        "input": {
            "images": [
                "https://assets-public.namifusion.com/uploads/images/2026-04-21/76c1186af77d.png",
                "https://assets-public.namifusion.com/uploads/images/2026-04-21/149467630166.png"
            ],
            "prompt": "Enhance the facial features while preserving natural skin tone and texture. Add soft lighting and a cinematic color grade.",
            "size": "4K",
            "aspect_ratio": "16:9"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.5/image-to-image", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "images": [
        "https://assets-public.namifusion.com/uploads/images/2026-04-21/76c1186af77d.png",
        "https://assets-public.namifusion.com/uploads/images/2026-04-21/149467630166.png"
      ],
      "prompt": "Enhance the facial features while preserving natural skin tone and texture. Add soft lighting and a cinematic color grade.",
      "size": "4K",
      "aspect_ratio": "16:9"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Documentazione API

Seedream 4.5 Edit

Professional, high-fidelity image editing with reference-faithful precision

Seedream 4.5 Edit is a high-end image-to-image editing model designed to deliver professional-grade results. It preserves facial features, lighting, and color tones from reference images while applying precise, prompt-driven edits. With support for resolutions up to 4K, strong prompt adherence, and batch processing capabilities, this model is ideal for creative professionals and businesses seeking high-quality visual transformations.


🚀 Key Features

  • Reference-faithful editing: Maintains identity, pose, lighting, and color palette from the original image.
  • Multi-image support: Edit up to 10 images simultaneously with consistent results across the batch.
  • High-fidelity details: Produces crisp textures, clean edges, and minimal artifacts even for complex edits.
  • Strong prompt adherence: Accurately interprets nuanced instructions for clothing, background, mood, and style changes.
  • 4K-ready output: Supports resolutions up to 8192 × 8192 pixels for ultra-detailed results.
  • No cold starts: Immediate performance with low latency.

🛠️ Technical Specifications

SpecificationDetails
Model ArchitectureProprietary image-to-image editing model
Input FormatArray of images (1–10 images)
Output FormatEdited images (PNG, JPEG)
Resolution512 × 512 to 8192 × 8192 pixels
PromptPositive prompt for specifying edits
LatencyLow latency, optimized for batch processing
Maximum Batch Size10 images

Sample Prompts

  • Outfit Change: "Change jacket to red leather, keep pose and background, cinematic lighting."
  • Background Replacement: "Replace background with a sunset beach scene, match original light direction."
  • Style Adjustment: "Apply vintage film color grading, keep subject identity and composition."

💰 Pricing

ResolutionPrice per Image
Up to 4K (8192 × 8192)$0.04

💡 Best Use Cases

  • Portrait retouching: Enhance facial features and lighting for beauty or fashion photography.
  • Outfit and accessory changes: Experiment with clothing styles and accessories.
  • Background replacement: Upgrade scenes for marketing or creative projects.
  • Product visual updates: Explore colorways and design variations for e-commerce.
  • Interior and architecture tweaks: Refine visuals for real estate or design portfolios.

🔗 Related Models

  • Seedream 4.5 Edit Sequential: Ensures consistent style across batch edits, ideal for series of portraits or product shots.
  • Flux 2 Flex/Edit: Offers creative restyling and mood shifts for art-direction-heavy projects.
  • Flux 2 Pro/Edit: Production-grade editing with multi-reference and context-aware control for complex composites.

Modelli correlati

xAI Grok Imagine Image v2.0 Edit
Immagine in immagineX Ai

xAI Grok Imagine Image v2.0 Edit

x-ai/grok-imagine-image-v2.0/edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.090 / per esecuzione
qwen-image-edit-spicy
Immagine in immagine

qwen-image-edit-spicy

qwen-image-edit-spicy. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.040 / per esecuzione
Qwen Image 3.0 Pro Edit | Fast Image Editing
Immagine in immagineQwen Image 3.0 Pro

Qwen Image 3.0 Pro Edit | Fast Image Editing

qwen-image-3.0-pro/edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.078 / per esecuzione
OpenAI GPT Image 2.5 Sunburst Edit
Immagine in immagineOpenAI

OpenAI GPT Image 2.5 Sunburst Edit

openai/gpt-image-2.5-sunburst/edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.220 / per esecuzione
OpenAI GPT Image 2.5 Flare Edit
Immagine in immagineOpenAI

OpenAI GPT Image 2.5 Flare Edit

openai/gpt-image-2.5-flare/edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.220 / per esecuzione
Immagine in immagine
Immagine in immagineNamiFusion

Head Swap (Image)

namifusion/head-swap/image-edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.220 / per esecuzione
Nano Banana Image Edit
Immagine in immagineGoogle

Nano Banana Image Edit

google/nano-banana/edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.038 / per esecuzione
Nano Banana Pro Image Edit
Immagine in immagineGoogle

Nano Banana Pro Image Edit

google/nano-banana-pro/edit. Esplora API di modelli per immagini, video e scambio volto. Prova un modello e integralo tramite un’unica API REST.

da $0.140 / per esecuzione