Model AI API ByteDance
Model AI ByteDance di MuAPI
Jelajahi model ByteDance untuk obrolan, kode, pembuatan gambar dan video, termasuk alur kerja bergaya Gemini, Nano Banana, dan Veo yang tersedia melalui MuAPI.
Semua model
90 ModelModel Pembuatan Video
$0.260 / detik
seedance-v1.5-pro-t2v-fast
Seedance v1.5 Pro Text-to-Video Fast generates short cinematic videos directly from text with an emphasis on speed and stability. It produces coherent scenes with simple camera motion, light environmental animation, and consistent lighting.
$0.750 / detik
seedance-2-i2v
SD 2.0 is the latest multimodal video generation model by ByteDance, offering advanced camera control, native audio-video sync, and high-resolution output. Selectable output resolution (480p/720p) — price scales with the resolution chosen.
$1.500 / detik
seedance-2-omni-reference
SD 2.0 Omni Reference — generate videos with visual consistency using reference images, videos, and audio. Maintain character identity, style, and scene continuity. Supports up to 9 images, 3 video clips, and 3 audio clips. Use @image1, @video1, @audio1 syntax in your prompt. Selectable output resolution (480p/720p/1080p/4k) — price scales with the resolution chosen.
$0.180 / detik
seedance-pro-i2v
Seedance Pro I2V advanced model animates still images into stunning short videos, preserving intricate visual details and applying smooth motion dynamics, ideal for high-end visuals and cinematic edits.
$0.750 / detik
seedance-2-image-to-video-fast
SD 2 Image-to-Video (Fast) by ByteDance. Quickly animates a start-frame image into video with 4–15 second duration at reduced cost.
$1.250 / detik
seedance-2-first-last-frame
SD 2 First & Last Frame (Pro) by ByteDance. Generate video that transitions between two reference images. Provide 1 image for start-frame-only, or 2 images for both start and end frames.
$1.050 / detik
seedance-2-vip-image-to-video-fast
SD 2 Image-to-Video VIP Fast by ByteDance. Faster animation of a start-frame image with priority routing, 4–15 second duration, and 2K resolution. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$1.050 / detik
seedance-2-vip-omni-reference-fast
SD 2 Omni Reference VIP Fast by ByteDance. Faster video generation using up to 9 image references, up to 3 video clips, and up to 3 audio references with priority routing. Reference materials in your prompt with @image1…@image9, @video1…@video3, and @audio1…@audio3. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$0.250 / detik
omnihuman-1-5
Generate realistic talking head video from portrait image and audio using OmniHuman 1.5.
$0.400 / detik
seedance-2.1-image-to-video
Seedance 2.1 Image-to-Video converts a single still image into a high-fidelity cinematic video. This next-generation model delivers enhanced temporal consistency, improved motion realism, and smarter prompt adherence — producing smooth, coherent clips up to 1080p.
$0.400 / detik
seedance-2.1-text-to-video
Seedance 2.1 Text-to-Video generates high-quality cinematic videos directly from text prompts. The model excels at complex scene composition, smooth temporal flow, and accurate prompt interpretation — producing vivid motion sequences up to 1080p with enhanced realism over the previous generation.
$0.060 / detik
seedance-pro-i2v-fast
Seedance Pro Fast is the high-speed image-to-video generation variant from ByteDance’s Seedance series. With this model you upload a reference image and—using a text prompt—generate short, dynamic video clips (typically 3-12 seconds) featuring smooth motion, cinematic camera moves, prompt-accurate actions, and high visual fidelity. It supports resolutions up to 1080p, multiple aspect ratios (16:9, 9:16, etc.), and rapid turnaround—ideal for social content, product motion, storytelling from a still, and fast prototyping.
$0.600 / detik
seedance-2.5-spicy-image-to-video
Seedance 2.5 Spicy Image-to-Video is the relaxed-moderation variant of the Seedance 2.5 flagship model. It animates a single image into photorealistic 4K video with reduced content-safety filtering and more dramatic, higher-contrast motion than the standard tier — while keeping native audio generation and precise camera trajectory control.
$1.700 / detik
seedance-2.5-video-extend
Seedance 2.5 Video Extend extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen.
$1.870 / detik
seedance-2.5-intl-image-to-video
Seedance 2.5 Image-to-Video animates a single image into video, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds. This international-region endpoint is served via a Dreamina-hosted deployment of the same Seedance 2.5 model, for traffic outside mainland China.
$1.870 / detik
seedance-2.5-intl-video-edit
Seedance 2.5 Video Edit edits an input video from a natural-language prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed. This international-region endpoint is served via a Dreamina-hosted deployment of the same Seedance 2.5 model, for traffic outside mainland China.
$1.500 / detik
seedance-2.5-motion-control
Recast an existing performance video with new performers while preserving the original motion, choreography, blocking, and camera work, and while keeping the original location. Upload a reference video plus character images of the new performers, and optionally a short instruction — the environment, motion, and camera work are automatically preserved and the identities are swapped.
$1.650 / detik
seedance-2.5-spicy-motion-control
Spicy Seedance 2.5 Motion Control — recast an existing performance video with a bolder creative treatment while preserving the original motion, choreography, blocking, camera work, and location. Upload a reference video plus character images and an optional short instruction.
$0.340 / detik
seedance-v1.5-pro-i2v
Seedance v1.5 Pro Image-to-Video converts a single still image into a smooth cinematic video clip. It preserves the original image’s composition, subject identity, and lighting while adding controlled camera motion, natural parallax, and environmental animation. This mode balances visual quality and motion complexity, making it ideal for cinematic scenes, fantasy worlds, sci-fi environments, and storytelling shots.
$0.340 / detik
seedance-v1.5-pro-t2v
Seedance v1.5 Pro Text-to-Video generates high-quality cinematic videos directly from text prompts. It focuses on smooth motion, rich atmosphere, and coherent scene structure, making it ideal for fantasy worlds, sci-fi environments, surreal visuals, and cinematic storytelling shots with detailed lighting and depth.
$0.260 / detik
seedance-v1.5-pro-i2v-fast
Seedance v1.5 Pro Image-to-Video Fast converts a single still image into a short cinematic video with quick generation speed. It preserves the original image’s composition, subject identity, and lighting while adding simple camera motion, light parallax, and subtle environmental animation.
$0.340 / detik
seedance-v1.5-pro-video-extend
Seedance v1.5 Pro Video Extend continues an existing video by generating additional frames that match the original scene’s style, lighting, motion, and mood. It is designed for smooth temporal consistency, making it ideal for extending cinematic shots, atmospheric scenes, or slow camera moves without introducing visual jumps or style changes.
$0.750 / detik
seedance-2-t2v
SD 2.0 is the latest multimodal video generation model by ByteDance, offering advanced camera control, native audio-video sync, and high-resolution output. Selectable output resolution (480p/720p) — price scales with the resolution chosen.
$0.025 / detik
seedance-2-watermark-remover
🎉 FREE for a limited time — Remove SD 2.0 watermarks from videos using LaMa AI inpainting. Automatically detects the watermark region, builds a precise mask via Canny edge detection, and inpaints each frame for artifact-free results. No credits deducted — requires a positive balance to access.
$1.500 / detik
seedance-2-video-edit
SD 2.0 Video Edit modifies existing videos based on text prompts and optional reference images.
$0.065 / detik
seedance-2-video-watermark-remover-pro
SD 2 Video Watermark Remover Pro uses the SD 2 AI model to remove watermarks, logos, and overlaid text from videos with high accuracy. Powered by ByteDance's SD 2 engine, it delivers superior quality compared to traditional inpainting approaches. Pricing: $0.013 per second, minimum charge for 5 seconds ($0.065).
$1.250 / detik
seedance-2-text-to-video
SD 2 Text-to-Video (Pro) by ByteDance. Generates high-quality cinematic video from a text prompt with native audio-visual sync, up to 2K resolution, and 4–15 second duration.
$1.250 / detik
seedance-2-image-to-video
SD 2 Image-to-Video (Pro) by ByteDance. Animates a start-frame image into a high-quality video with native audio, 4–15 second duration, and 2K resolution.
$0.750 / detik
seedance-2-first-last-frame-fast
SD 2 First & Last Frame (Fast) by ByteDance. Quickly generate video that transitions between reference images at reduced cost. Provide 1 or 2 images.
$1.250 / detik
seedance-2-omni-reference-no-video
SD 2 Omni Reference by ByteDance. Generate videos using up to 9 image references and up to 3 audio references. Reference images in your prompt with @image1, @image2, etc. and audio with @audio1, @audio2, etc.
$0.750 / detik
seedance-2-omni-reference-no-video-fast
SD 2 Omni Reference (Fast) by ByteDance. Quickly generate videos using up to 9 image references and up to 3 audio references at reduced cost. Reference images in your prompt with @image1, @image2, etc. and audio with @audio1, @audio2, etc.
$1.500 / detik
seedance-2-vip-text-to-video
SD 2 Text-to-Video VIP (Pro) by ByteDance. Generates high-quality cinematic video from a text prompt with priority routing, native audio-visual sync, up to 2K resolution, and 4–15 second duration. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$0.100 / detik
seedance-lite-i2v
Seedance Lite I2V version animates static images into short videos quickly, focusing on basic motion effects and efficient processing—best suited for fast demos or mobile-friendly use.
$1.700 / detik
seedance-2.5-image-to-video
Seedance 2.5 Image-to-Video animates a single image into video, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds.
$1.700 / detik
seedance-2.5-text-to-video
Seedance 2.5 Text-to-Video generates cinematic video directly from a detailed text prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds.
$0.200 / detik
seedance-2-mini-image-to-video
Seedance 2.0 Mini Image-to-Video is the fastest and most cost-efficient tier in the Seedance 2.0 family, converting still images into smooth cinematic video clips at up to 720p. Roughly 2x faster than Seedance 2.0 Fast, it is purpose-built for high-volume production, rapid iteration, and draft workflows.
$0.200 / detik
seedance-2-mini-text-to-video
Seedance 2.0 Mini Text-to-Video is the fastest and most affordable text-to-video model in the Seedance lineup, generating smooth 720p video clips from text prompts. Designed for rapid iteration and high-volume workflows, it delivers approximately 2x faster generation than Seedance 2.0 Fast at a fraction of the cost.
$0.100 / detik
seedance-lite-t2v
Seedance Lite T2V offers quick video generation from text with decent visual quality and motion. Ideal for fast previews, prototyping, or lightweight use cases where speed matters more than fine detail.
$0.150 / detik
seedance-2-mini-omni-reference
Seedance 2 Mini Omni Reference generates video from a text prompt with optional image, video, and audio references. Cost-efficient mini-tier model for reference-driven workflows.
$0.180 / detik
seedance-pro-t2v
Seedance Pro delivers high-fidelity video generation from text, producing rich visuals, smooth camera movement, and realistic scenes. Best for storytelling, content creation, and visual production.
$0.100 / detik
seedance-lite-reference-video
Seedance Lite's Reference-to-Video feature allows you to supply up to 4 images as reference inputs. The model intelligently blends aspects from these images to generate a cohesive, high-quality video.
$1.650 / detik
seedance-2-spicy-image-to-video
Seedance 2 Spicy Image-to-Video by ByteDance. Animates a start frame into cinematic video with VIP-tier priority routing and up to 2K resolution, with reduced content-safety filtering for more creative freedom.
$0.060 / detik
seedance-pro-t2v-fast
Seedance Pro Fast is ByteDance’s advanced text-to-video model that turns natural-language prompts into short, cinematic video clips with realistic motion, camera dynamics, and consistent scene detail.
$0.220 / detik
seedance-2-mini-spicy-image-to-video
Seedance 2 Mini Spicy Image-to-Video is the fastest, lowest-cost Spicy-tier image animation, with reduced content-safety filtering on top of Seedance 2 Mini's speed and pricing.
$1.650 / detik
seedance-2.5-intl-motion-control
International-region Seedance 2.5 Motion Control — recast an existing performance video with new performers while preserving the original motion, choreography, blocking, camera work, and location. Upload a reference video plus character images and an optional short instruction.
$1.155 / detik
seedance-2-spicy-image-to-video-fast
Seedance 2 Spicy Image-to-Video Fast by ByteDance. The quickest Spicy-tier image animation, with reduced content-safety filtering and the same fast queue as Seedance 2 VIP Fast.
$0.260 / detik
seedance-v1.5-pro-video-extend-fast
Seedance v1.5 Pro Video Extend Fast quickly extends an existing video by generating a short continuation that matches the original style, motion, and lighting. This mode prioritizes fast output and smooth continuity with minimal new motion, making it ideal for previews, quick edits, and lightweight shot extensions without complex effects.
$0.600 / detik
seedance-2.5-spicy-text-to-video
Seedance 2.5 Spicy Text-to-Video is the relaxed-moderation variant of the Seedance 2.5 flagship model, generating photorealistic 4K cinematic video directly from a text prompt with reduced content-safety filtering and more dramatic, higher-contrast motion than the standard tier — while retaining native audio synthesis and extended clip durations.
$1.650 / detik
seedance-2-spicy-text-to-video
Seedance 2 Spicy Text-to-Video by ByteDance. Same VIP-tier priority routing, native audio-visual sync, and up to 2K resolution as Seedance 2 VIP, with reduced content-safety filtering for more creative freedom.
$1.155 / detik
seedance-2-spicy-text-to-video-fast
Seedance 2 Spicy Text-to-Video Fast by ByteDance. The quickest Spicy-tier text-to-video generation, with reduced content-safety filtering and the same fast queue as Seedance 2 VIP Fast.
$1.700 / detik
seedance-2.5-first-last-frame
Seedance 2.5 First & Last Frame generates a smooth video transition between a start and end image, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds.
$0.220 / detik
seedance-2-mini-spicy-text-to-video
Seedance 2 Mini Spicy Text-to-Video is the fastest, lowest-cost Spicy-tier text-to-video generation, with reduced content-safety filtering on top of Seedance 2 Mini's speed and pricing.
$1.050 / detik
seedance-2-extend
SD 2.0 Extend Video continues an existing SD 2.0 generated video seamlessly. Provide the original request ID and an optional prompt to guide the extension — the model preserves visual style, motion, characters, and audio consistency across the new segment. Optional image, video, and audio references can be supplied to steer the extension: user-supplied references map to @image2…@image9, @video1…@video3, @audio1…@audio3 in the prompt (the source video's last frame is always @image1).
$1.870 / detik
seedance-2.5-intl-text-to-video
Seedance 2.5 Text-to-Video generates cinematic video directly from a detailed text prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds. This international-region endpoint is served via a Dreamina-hosted deployment of the same Seedance 2.5 model, for traffic outside mainland China.
$1.500 / detik
seedance-2-vip-image-to-video
SD 2 Image-to-Video VIP (Pro) by ByteDance. Animates a start-frame image into a high-quality video with priority routing, native audio, 4–15 second duration, and 2K resolution. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$0.750 / detik
seedance-2-text-to-video-fast
SD 2 Text-to-Video (Fast) by ByteDance. Generates video from text at faster speeds with 4–15 second duration and 2K resolution.
$1.700 / detik
seedance-2.5-video-edit
Seedance 2.5 Video Edit edits an input video from a natural-language prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed.
$1.500 / detik
seedance-2-vip-first-last-frame
SD 2 First & Last Frame VIP (Pro) by ByteDance. Generate video that transitions between two reference images with priority routing. Provide 1 image for start-frame-only, or 2 images for both start and end frames. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$1.050 / detik
seedance-2-vip-first-last-frame-fast
SD 2 First & Last Frame VIP Fast by ByteDance. Faster generation of video transitions between two reference images with priority routing.
$1.870 / detik
seedance-2.5-intl-omni-reference
Seedance 2.5 Omni Reference blends multiple reference images, video clips, and audio into a single guided generation, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds. This international-region endpoint is served via a Dreamina-hosted deployment of the same Seedance 2.5 model, for traffic outside mainland China.
$1.050 / detik
seedance-2-vip-text-to-video-fast
SD 2 Text-to-Video VIP Fast by ByteDance. Faster generation with priority routing from a text prompt, 4–15 second duration and 2K resolution. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$1.500 / detik
seedance-2-vip-omni-reference
SD 2 Omni Reference VIP (Pro) by ByteDance. Generate videos using up to 9 image references, up to 3 video clips, and up to 3 audio references with priority routing. Reference materials in your prompt with @image1…@image9, @video1…@video3, and @audio1…@audio3. Also supports @omni-character:<char_id> for trained characters. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$1.870 / detik
seedance-2.5-spicy-video-edit
Seedance 2.5 Video Edit edits an input video from a natural-language prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed. This Spicy endpoint is the relaxed-moderation sibling of the standard tier, with lighter content-safety filtering and bolder, higher-contrast output.
$1.870 / detik
seedance-2.5-spicy-omni-reference
Seedance 2.5 Omni Reference blends multiple reference images, video clips, and audio into a single guided generation, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds. This Spicy endpoint is the relaxed-moderation sibling of the standard tier, with lighter content-safety filtering and bolder, higher-contrast output.
$1.870 / detik
seedance-2.5-spicy-video-extend
Seedance 2.5 Video Extend extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. This Spicy endpoint is the relaxed-moderation sibling of the standard tier, with lighter content-safety filtering and bolder, higher-contrast output.
$1.050 / detik
seedance-2-vip-extend
SD 2.0 VIP Extend Video continues an existing SD 2.0 generated video seamlessly at 720p. Provide the original request ID and an optional prompt to guide the extension — the model preserves visual style, motion, characters, and audio consistency across the new segment. Optional image, video, and audio references can be supplied to steer the extension: user-supplied references map to @image2…@image9, @video1…@video3, @audio1…@audio3 in the prompt (the source video's last frame is always @image1). Selectable output resolution (720p/1080p) — price scales with the resolution chosen.
$1.700 / detik
seedance-2.5-omni-reference
Seedance 2.5 Omni Reference blends multiple reference images, video clips, and audio into a single guided generation, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds.
$1.870 / detik
seedance-2.5-intl-first-last-frame
Seedance 2.5 First & Last Frame generates a smooth video transition between a start and end image, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds. This international-region endpoint is served via a Dreamina-hosted deployment of the same Seedance 2.5 model, for traffic outside mainland China.
$1.870 / detik
seedance-2.5-spicy-first-last-frame
Seedance 2.5 First & Last Frame generates a smooth video transition between a start and end image, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds. This Spicy endpoint is the relaxed-moderation sibling of the standard tier, with lighter content-safety filtering and bolder, higher-contrast output.
$1.870 / detik
seedance-2.5-intl-video-extend
Seedance 2.5 Video Extend extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. This international-region endpoint is served via a Dreamina-hosted deployment of the same Seedance 2.5 model, for traffic outside mainland China.
$1.000 / detik
seedance-2-motion-control
Recast an existing performance video with new performers while preserving the original motion, choreography, blocking, and camera work, and while keeping the original location. Upload a reference video plus character images of the new performers, and optionally a short instruction — the environment, motion, and camera work are automatically preserved and the identities are swapped.
$1.500 / detik
seedance-2-spicy-omni-reference
Seedance 2 Spicy Omni Reference by ByteDance. Same VIP-tier priority routing as Seedance 2 VIP Omni Reference, generating videos from up to 9 image references, 3 video clips, and 3 audio references, with reduced content-safety filtering for more creative freedom. Reference materials in your prompt with @image1…@image9, @video1…@video3, and @audio1…@audio3. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$1.050 / detik
seedance-2-spicy-omni-reference-fast
Seedance 2 Spicy Omni Reference Fast by ByteDance. Faster video generation using up to 9 image references, up to 3 video clips, and up to 3 audio references with priority routing, and reduced content-safety filtering for more creative freedom. Reference materials in your prompt with @image1…@image9, @video1…@video3, and @audio1…@audio3. Selectable output resolution (720p/1080p/4K) — price scales with the resolution chosen.
$0.750 / detik
seedance-2-mini-spicy-omni-reference
Seedance 2 Mini Spicy Omni Reference generates video from a text prompt with optional image, video, and audio references. Cost-efficient mini-tier model for reference-driven workflows, with reduced content-safety filtering for more creative freedom.
Model Pembuatan Gambar
$0.030 / 1K token
bytedance-seedream-v3
Seedream is designed for generating visually rich and artistic images from text prompts. It excels at fantasy, anime, surrealism, and vibrant color compositions — ideal for creative visuals, storyboards, and concept art.
$0.030 / generasi
bytedance-seededit-v3
Seededit allows precise edits to images using masks and prompt guidance. Whether you're replacing backgrounds, changing clothing, or inpainting missing areas, Seededit ensures realistic, high-quality results with semantic control.
$0.040 / 1K token
bytedance-seedream-v4
Seedream v4 generates stunning, high-fidelity images from text prompts. It’s designed for creativity with strong support for realism, fantasy, and artistic styles.
$0.045 / 1K token
bytedance-seedream-5.0-pro
Seedream 5.0 Pro is ByteDance's flagship next-generation text-to-image model, extending Seedream 5.0 Lite with higher-fidelity rendering, deeper visual reasoning, and finer typography control. It targets up to 2K output with stronger scene composition, more consistent multi-character generation, and richer prompt adherence for professional creative workflows.
$0.045 / generasi
bytedance-seedream-5.0-pro-edit
Seedream 5.0 Pro Edit is ByteDance's flagship image editing model, extending Seedream 5.0 Lite Edit with higher-fidelity rendering, deeper visual reasoning, and finer typography control. It accepts one or more reference images and a natural-language instruction, targeting up to 2K output with stronger scene composition and richer prompt adherence for professional creative workflows.
$0.033 / generasi
bytedance-seedream-v5.0-edit
Seedream 5.0 Lite Edit is an advanced image transformation model by ByteDance, enabling precise, controllable edits using natural language. It specializes in high-fidelity style transfer (Anime, Cyberpunk, Fantasy), background swaps, and object modification while preserving original lighting, color tones, and character consistency for professional-grade creative reworks.
$0.180 / generasi
seedance-2-character
[Beta] Turn fictional character references into reusable video characters. Upload reference images and describe the outfit to get a character_id you can use in SD 2.0 Omni Reference.
$0.500 / generasi
seedance-2-omni-reference-train
Train a reusable character from a reference photo. Once complete, reference the character in Omni Reference video prompts using @omni-character:<request_id> to generate videos featuring that character consistently.
$0.040 / generasi
bytedance-seedream-v4-edit
Seedream v4 Edit refines or transforms existing images based on a new prompt and a reference. Instead of masking, you provide a source image and describe how it should be altered — adjusting style, details, or replacing elements while keeping the subject consistent.
$0.050 / generasi
bytedance-seedream-v4.5-edit
Seedream-v4.5 Edit allows you to transform an existing image using natural-language instructions. It preserves the core composition, lighting, and style of the original while modifying only the requested elements — perfect for object replacement, environment changes, stylistic adjustments, and high-detail creative reworks.
$0.050 / 1K token
bytedance-seedream-v4.5
Seedream-v4.5 is ByteDance’s advanced text-to-image diffusion model designed for generating high-detail, high-contrast, cinematic and stylized images. It excels at surreal fantasy concepts, sci-fi worlds, product visuals, photoreal scenes, and artistic compositions with strong prompt adherence and crisp detail.
$0.033 / 1K token
bytedance-seedream-v5.0
Seedream 5.0 Lite is ByteDance’s next-generation text-to-image model, delivering high-fidelity AI art with advanced visual reasoning and precise typography. Supporting up to 4K resolution and cinematic detail, it excels at complex scene construction, consistent character generation, and real-time knowledge integration for accurate, contextually relevant visuals.
$0.045 / generasi
bytedance-seedream-5.0-pro-layer
Decompose complex images into clean, editable multi-layer assets with ByteDance Seedream 5 Pro Layer Decomposition.
$0.027 / 1K token
seedream-5.0-flash
Seedream 5.0 Flash is ByteDance's fast, low-cost Seedream 5 text-to-image tier, delivering photorealistic 1K and 2K images with strong prompt adherence and in-image text for high-volume creative workflows.
$0.027 / generasi
seedream-5.0-flash-edit
Seedream 5.0 Flash Edit is ByteDance's fast, low-cost image-to-image tier, editing or combining up to 10 reference images from a text instruction at 1K or 2K.
$0.459 / generasi
seedream-5.0-flash-layerize
Decompose a composite image into a base image plus clean, separate layer assets with Seedream 5.0 Flash Layer Decomposition. Optionally target elements with prompts or <bbox> regions.