Seedream 4.5 Edit preserves facial features, lighting, and color tone from reference images, delivering professional, high-fidelity edits up to 4K with strong prompt adherence. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
ว่าง

$0.04ต่อครั้ง·~25 / $1

Keep the model's pose and the flowing shape of the liquid clothing unchanged. Change the clothing material from silver metal to completely transparent clear water (or glass). Through the liquid water flow, the details of the model's skin can be seen. The light and shadow change from reflection to refraction. Remove the watermark. change the background to a night city.

it this image into a luxurious night-time black & gold campaign visual. Keep the same serum bottle and cream jar in their original positions, shapes and reflections, but place them on a glossy black marble surface with subtle golden highlights and a soft glow around the base of the products. Replace the bright background with a dark, slightly blurred gradient from deep charcoal to rich gold, with a few soft bokeh lights suggesting a glamorous evening atmosphere. Update the typography to match the new style: keep the brand name ‘LUMINA SKIN’ at the top in elegant gold serif letters, and keep the lines ‘Hydrating Renewal Serum’ and ‘Daily Radiance Care’ below in clean white sans-serif. At the bottom, keep the tagline ‘Lightweight serum formula · suitable for all skin types’ in small, sharp white text, perfectly legible. Overall: high-contrast black and gold color palette, premium beauty advertising style, ultra-realistic lighting and reflections, 4K, no extra elements.

Edit this image into a futuristic tech headquarters lobby at night. Keep the original architecture, marble materials, curved reception desk, and overall perspective, as well as the city skyline visible through the glass. Transform the glowing logo on the central column into a sleek holographic emblem and add the golden brand name ‘SEQUENCE LABS’ subtly integrated beneath it in clean sans-serif typography, sharp and legible. Add a few translucent holographic information panels floating near the reception desk and along the balconies, showing minimal graphs and icons without readable detailed text. Slightly intensify the warm indirect lighting and add soft cyan accents to the holograms, reflections on the floor, and edges of the columns, while preserving a realistic photographic look. Keep the people as elegant silhouettes in business attire, walking or talking, not the main focus. Overall mood: premium, minimalist, cinematic tech-company lobby, 4K, no extra clutter.

Edit this image into a high-end futuristic fragrance campaign visual, 4K resolution. Keep the original desert setting, the tall mirrors, and the two models with their sculptural gowns and metallic bodices, preserving their poses and faces. In the center foreground, between the two models and slightly closer to the camera, add a tall, elegant glass perfume bottle standing on the sand, filled with softly glowing lilac liquid that reflects the neon ring and mirror lights. Slightly intensify the sunset colors into a richer gradient of pink, lilac, and deep blue, and add subtle glowing edges around the mirrors and circular light on the sand for a more surreal, futuristic mood, while maintaining a realistic photographic look. At the top center, add the brand name ‘MIRAGE’ in refined serif typography, sharp and clean. At the bottom, add a small tagline in white sans-serif: ‘Eau de Parfum — Beyond Reality’. Overall style: luxury fashion fragrance advertisement, cinematic lighting, smooth skin tones, crisp details, no other elements or logos.

dit this image into a clean, minimal exhibition poster without any meaningless filler text. Keep the desert landscape, the two standing figures, the mirrors, and the glowing neon circle in the center, preserving the overall composition and realistic photographic style. Simplify the typography: keep only the main title ‘DESERT REFLECTIONS’ at the top in bold white sans-serif, and one short subtitle under it: ‘New Media Installations by Studio Meridian’. Remove all other small blocks of text from the sky area so the design feels spacious and minimal. Slightly enhance the sky with a soft gradient from pale blue to turquoise and add a subtle hint of tiny stars for a dreamy atmosphere, with gentle grain and high-end art poster look, no extra logos or text.
Seedream 4.5 Edit is ’s high-end image editing model. It preserves facial structure, lighting, and colour tone from your input while applying precise, prompt-driven changes that look like they were done by a professional retoucher—not an over-filtered AI.
Flat, simple pricing:
Each successfully edited output counts as one image.
Upload images Add 1–10 images under images. These are the photos that will be edited.
Write your edit prompt Clearly describe what should change and what must stay the same, e.g. “Change jacket to red leather, keep pose and background, cinematic lighting.”
(Optional) Set size
Outfit / accessory change
Change outfit to {DESCRIPTION}, keep pose and lighting, preserve skin tone, clean edges, no distortions.
Background replacement
Replace background with {SCENE}, match original light direction, natural shadows, no haloing around subject.
Style / mood change
Apply {STYLE} colour grading, keep subject identity and composition, subtle filmic contrast, rich details.
Product recolour
Change product colour to {HEX / COLOUR NAME}, keep material and reflections, no change to logo.
Use Seedream 4.5 Edit together with other editing models depending on what you’re optimising for:
/seedream-v4.5/edit-sequential – multi-image editing that keeps the same character and style across a whole batch; best when you need a series of consistent portraits, product shots or KV variations.
wavespeed-ai/flux-2-dev/edit – lightweight FLUX.2 edit model for fast, low-cost batch updates; great for everyday asset tweaks where ultimate fidelity is less critical.
flux-2-flex/edit – more style-rich and adventurous editing; good for creative restyling, mood shifts and art-direction heavy work rather than strict realism.
flux-2-pro/edit – production-grade FLUX.2 editing with multi-reference and context-aware control, suited to complex commercial composites and e-commerce pipelines.
qwen-image/edit-plus – strong semantic understanding and local control, ideal for masking-style edits, UI mockups, and precise object-level changes.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5/edit with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Seedream v4.5 Edit below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5/edit" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"enable_sync_mode": false,
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("bytedance/seedream-v4.5/edit", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"enable_sync_mode": false,
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bytedance/seedream-v4.5/edit",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"enable_sync_mode": false,
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputSeedream v4.5 Edit is a ByteDance model for image editing, exposed as a REST API on WaveSpeedAI. Seedream 4.5 Edit preserves facial features, lighting, and color tone from reference images, delivering professional, high-fidelity edits up to 4K with strong prompt adherence. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4.5-edit.
Seedream v4.5 Edit starts at $0.040 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `enable_base64_output`, `enable_sync_mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4.5-edit.
Average end-to-end generation time on WaveSpeedAI is around 19 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.