WaveSpeed.ai
Beranda/Jelajahi/Seedream AI Models/bytedance/seedream-v4.5/edit-sequential
image-to-image

image-to-image

ByteDance Seedream 4.5 Edit Sequential

bytedance/seedream-v4.5/edit-sequential

Seedream 4.5 Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Input

Hint: You can drag and drop a file or click to upload

preview
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

Create a sequence of 2 CG animated-style images based on the provided photo. Keep the same tall rectangular building, the still water, heavy fog, and overall composition in both images. The scene must remain in the same location and perspective, only the atmosphere, lighting and supernatural elements should change. Style: cinematic 3D animation, slightly stylized but realistic materials, cool blue-green palette, strong Cthulhu / cosmic horror mood. Image 1 – ‘Omen’: Night-time foggy scene. The building stands in the water as in the reference, but the single lit window glows a faint sickly green instead of warm yellow. In the dark water near the base of the building, add very subtle hints of enormous tentacles just beneath the surface, their shapes barely visible through the misty reflections. Faint glowing eldritch runes appear vertically along the central line of the building’s facade, dim and eerie. The overall lighting is low, mysterious and quiet. Image 2 – ‘Awakening’: Same angle and building, but the fog now glows with an unnatural turquoise-green light. Large shadowy tentacles rise clearly from the water around the base, curling toward the tower and partly wrapping around it. The runes on the facade burn much brighter, and a massive circular eye-like glow appears high on the building, staring toward the viewer. The water reflects distorted green light and ripples outward. The sky remains lost in fog, but with darker shapes hinting at something colossal beyond. Both images should look like frames from the same animated Cthulhu-inspired short film, with consistent building design, water surface and atmospheric style.
Create a sequence of 2 CG animated-style images based on the provided photo. Keep the same tall rectangular building, the still water, heavy fog, and overall composition in both images. The scene must remain in the same location and perspective, only the atmosphere, lighting and supernatural elements should change. Style: cinematic 3D animation, slightly stylized but realistic materials, cool blue-green palette, strong Cthulhu / cosmic horror mood. Image 1 – ‘Omen’: Night-time foggy scene. The building stands in the water as in the reference, but the single lit window glows a faint sickly green instead of warm yellow. In the dark water near the base of the building, add very subtle hints of enormous tentacles just beneath the surface, their shapes barely visible through the misty reflections. Faint glowing eldritch runes appear vertically along the central line of the building’s facade, dim and eerie. The overall lighting is low, mysterious and quiet. Image 2 – ‘Awakening’: Same angle and building, but the fog now glows with an unnatural turquoise-green light. Large shadowy tentacles rise clearly from the water around the base, curling toward the tower and partly wrapping around it. The runes on the facade burn much brighter, and a massive circular eye-like glow appears high on the building, staring toward the viewer. The water reflects distorted green light and ripples outward. The sky remains lost in fog, but with darker shapes hinting at something colossal beyond. Both images should look like frames from the same animated Cthulhu-inspired short film, with consistent building design, water surface and atmospheric style.

Permintaan Anda akan membutuhkan $0.04 per run.

Untuk $1 Anda dapat menjalankan model ini sekitar 25 kali.

Satu lagi hal::

ContohLihat semua

Create a sequence of 2 CG animated-style images based on the provided photo. Keep the same tall rectangular building, the still water, heavy fog, and overall composition in both images. The scene must remain in the same location and perspective, only the atmosphere, lighting and supernatural elements should change. Style: cinematic 3D animation, slightly stylized but realistic materials, cool blue-green palette, strong Cthulhu / cosmic horror mood. Image 1 – ‘Omen’: Night-time foggy scene. The building stands in the water as in the reference, but the single lit window glows a faint sickly green instead of warm yellow. In the dark water near the base of the building, add very subtle hints of enormous tentacles just beneath the surface, their shapes barely visible through the misty reflections. Faint glowing eldritch runes appear vertically along the central line of the building’s facade, dim and eerie. The overall lighting is low, mysterious and quiet. Image 2 – ‘Awakening’: Same angle and building, but the fog now glows with an unnatural turquoise-green light. Large shadowy tentacles rise clearly from the water around the base, curling toward the tower and partly wrapping around it. The runes on the facade burn much brighter, and a massive circular eye-like glow appears high on the building, staring toward the viewer. The water reflects distorted green light and ripples outward. The sky remains lost in fog, but with darker shapes hinting at something colossal beyond. Both images should look like frames from the same animated Cthulhu-inspired short film, with consistent building design, water surface and atmospheric style.
Create a sequence of 2 images in a soft comic style using the provided portrait as the main character reference. Maintain the same girl’s face, expression range, eye color and hair style in both images. Her age and appearance must remain natural and unchanged. Overall style: gentle shōjo manga / watercolor comic, pastel colors, soft outlines, subtle film grain, dreamy and calm mood. Image 1: Close-up half-body shot of the girl standing in the same meadow at golden hour, inspired by the reference. She looks slightly to the side, a light breeze moving a few strands of her hair, soft sunlight and blurred wildflowers behind her. Image 2: Wider shot in the same meadow and lighting. The girl is now standing a bit farther from the camera, holding a small bouquet of wildflowers in front of her, with more of the field and sky visible. Her expression is gently smiling and hopeful. The background and color palette should clearly match Image 1 so they feel like two consecutive moments from the same short comic, with no text or speech bubbles.
Create a sequence of 2 vertical 4K poster images using the provided perfume bottle as the hero product. The bottle’s shape, glass, cap, label design and logo must remain exactly the same in both images, only the environment, colors and mood should change. Image 1 – ‘Daylight Minimal’: Place the bottle on a clean white marble surface similar to the reference, with soft natural daylight coming from the left, casting a long gentle shadow. Background is bright and minimal, slightly out of focus, with very subtle warm reflections on the glass. No extra props. Add small, sharp text near the top in elegant black serif: ‘Eau de Parfum’. At the bottom, smaller sans-serif text: ‘Daylight Edition’. Overall style: high-end, clean, minimal luxury product photography. Image 2 – ‘Night Black & Gold’: Use the same bottle in the same scale and angle, but now on a glossy black surface with a rich dark background. Add a soft golden spotlight from the right, creating strong contrast and a dramatic, elongated highlight on the glass. Include a faint bokeh of golden lights in the background for a night-time, glamorous mood. Add small, sharp gold text near the top: ‘Eau de Parfum’. At the bottom, smaller white sans-serif text: ‘Noir Edition’. Overall style: luxurious black-and-gold campaign visual, cinematic and dramatic. Keep the product perfectly consistent between the two posters so they clearly feel like a coordinated day & night series for the same perfume brand.
Create a sequence of 2 cinematic images based on the uploaded photo. Keep the same young woman, her face, hairstyle and clothing perfectly consistent in both frames, and keep the rainy night window setting recognizable. Image 1: Close-up similar to the original, she sits by the rainy window at night, tears visible on her cheek, looking down with a heavy, lonely expression. Warm lamp light on one side of her face and cool blue city lights reflected in the glass, moody, realistic film look with soft grain. Image 2: The same scene a little later, but now it is early dawn. The rain has stopped and the sky outside is turning pale blue and pink, raindrops still on the glass. The camera is slightly wider, showing a bit more of her shoulders and the window. She looks up toward the light with a faint, fragile smile, eyes still wet but calmer, suggesting a small sense of hope. Softer, brighter lighting, gentle film grain, no text in either image. Image 3: The same woman now outside in the city during the morning, standing near a street or bus stop. She wears the same clothes, hair slightly moved by a light breeze. The sky is bright but soft, puddles on the ground reflecting buildings and light. She looks toward the camera with a quiet, peaceful smile, no more tears, carrying a sense of new beginning. Realistic cinematic style, natural daylight, subtle grain, no text in any image.

README

bytedance/seedream-v4.5/edit-sequential

Seedream 4.5 Edit Sequential is ByteDance’s multi-image editing model designed to apply the same edit across a whole set of images. It automatically tracks the main subject through the series, keeps identity stable, and generates clean, high-resolution results—ideal for campaigns, product sets, and character line-ups.

Model highlights

  • Multi-image subject tracking – Detects the main subject across all input images and treats them as the same person or object.
  • Character consistency lock – Preserves facial structure, proportions, and overall identity across every edited output.
  • High reference fidelity – Maintains lighting, colour balance, and key visual details while applying the requested changes.
  • Controlled, repeatable edits – One prompt drives a consistent transformation across the entire batch.
  • 4K-ready resolution – Supports sizes up to 4096 × 4096 for print-adjacent and hero visual use.
  • Production quality – Sharp edges, low artifacts, and stable composition suitable for professional workflows.

Best suited for

  • Batch portrait editing with a fixed style or look
  • Product series images that must feel like one coherent set
  • Brand or ad campaign iterations with the same model or hero product
  • Character design variations (outfits, moods, lighting)
  • E-commerce catalog refreshes and seasonal updates
  • Social / marketing visual series where continuity matters

Pricing

Billing is per output image, scaled by the max_images you request.

  • Base price: $0.04 per image
  • Formula: total_price = $0.04 × max_images

Example costs:

max_imagesTotal price
1$0.04
4$0.16
8$0.32

How to use

  1. Upload source images Add the images you want to edit sequentially (all should contain the same main subject or product).

  2. Write the edit prompt Describe the shared change you want across the whole set, e.g. “Change outfit to a black suit, add soft studio lighting, keep poses and background the same.”

  3. Set max_images Specify how many edited outputs you want the model to generate from your input set.

  4. Choose size Select the target resolution, up to 4096 × 4096 for maximum detail.

  5. Run and review Submit the job, inspect the edited series, and optionally refine the prompt for another pass.

Tips for best results

  • Use clear, global instructions in the prompt (“add winter outfit and snow ambience”) rather than per-image directions.
  • Keep input images reasonably consistent in framing and lighting so the model can lock onto the same subject.
  • Put your cleanest, clearest reference image first; the model tends to rely on it most strongly for identity.
  • For campaign work, generate at the highest resolution you need once, then downscale for web or social formats.

Note

  • Please set the max_image first, and then input how many images you want to generate in prompt! Such as:

  • max_image = 4. Prompt: I want to generate 4 images... + (your prompt)

More Models to Try!

  • Nano Banana Pro

    Google’s ultra, fast text-to-image model for generating many ideas from scratch; great for large batches of new images, not for editing existing photo series.

  • Seedream V4

    ByteDance’s high-resolution text-to-image generator with rich detail and diverse styles; ideal when you want new scenes in the Seedream aesthetic rather than editing your own photos.

  • Qwen Image Edit Plus

    Single-image, prompt-based editing with strong semantic understanding; perfect for one-off or small-batch edits where you don’t need strict identity matching across many images.