Is Seedance 1.5 Pro Spicy really uncensored for NSFW video?

There is no content review on our side, no mature switch and no per-request declaration. What you can make is decided by the model. Seedance's own safety layer still refuses a narrow band of wording — kissing most consistently — which is why an opening frame is the reliable route here.

What does camera_fixed do?

It stops the camera. Left false, the model adds its own drift or push; set true and the frame holds absolutely still while the subject moves inside it. For point-of-view scenes that is the difference between a shot that feels personal and one that reads as a music video.

Do I have to send a prompt?

No. image_url is the only required field; send it alone and the still moves on its own. A prompt makes that motion specific, and with the camera locked it should describe only things inside the frame — a breath, a hand, a shift of weight.

How long and how large can a clip be?

4 to 12 whole seconds, at 480p, 720p or 1080p. There is no 4k on this generation and nothing longer than twelve seconds. For 4K or thirty-second takes, use the 2.5 Spicy family, which has no camera lock.

Why did my request come back rejected?

Almost always Seedance's own safety layer refusing the wording before anything renders, not a schema problem. Rewrite so the frame shows the beat and the prompt only moves it, or take that shot to a Wan family, which accepts wording Seedance turns down.

How do I make a clean loop?

Set camera_fixed true, send the same still as both image_url and last_image_url, and keep the described motion small. A locked frame plus a small movement returns close to where it began, so the cut back to the start is invisible.

How do I keep the same character across several clips?

Reuse the same opening still. The likeness lives in the frame, so a set built from one still stays one person with no reference machinery — and this generation has no reference endpoint anyway. Change the prompt for each beat and pin the seed to compare takes.

Does it generate sound?

Yes, in the same pass as the picture. generate_audio defaults to true and produces room tone, movement and breath locked to the frames. It moves the request into a higher rate tier, so switch it off for silent loops.

Seedance 1.5 Pro Spicy API — Uncensored NSFW Video

bytedance/seedance-1.5-pro-spicy/video-extend

Continue a clip with Seedance 1.5 Pro Spicy: the last frame of your video opens a new 4 to 12 second segment, and you get back one file with the original and the continuation joined, at 480p / 720p / 1080p.

From $0.012/s

Run model View API

Input

Video extension

1
Pick the clip to continue
Pick a video and we’ll keep it going from its last frame.
2
What happens next
Pick a clip in step 1 and this step opens.
Model
Prompt
Optional. What happens next: the action that follows, the camera move and the sound. The opening frame already fixes the subject and the set, so spend the words on motion. Leave it empty and the model continues the shot on its own.
Durationaffects price
Length of the new segment in whole seconds, 4 to 12, default 5, and the billed quantity. Your source is added on top and is not billed. One frame drives the shot, so check the motion at 4 or 5 seconds before paying for 12. no lower than 4 · no higher than 12
Resolutionaffects price
Resolution of the new segment: 480p / 720p / 1080p, default 720p. Match your source: it only sets the quality of the new segment. The joined file keeps your clip’s framing with no black bars; to line the seam up, the picture may be trimmed or adjusted by a few percent at the edges. If the model returns a noticeably different shape, the new segment is scaled to fill your frame and centered, cropping what spills over. It sets the price.
Generate audioaffects price
On by default, so the new segment comes with generated sound. Your source keeps its own sound either way; when one side is silent, the joined file is padded with silence. On, it moves the request into a higher price tier; switch it off for silent loops and while checking framing.
Closing frame0/1
Asset URL
Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP · GIF
0 / 1 files
Optional target closing frame: the new segment lands on this picture, for a transition or a loop back to a known image. Keep camera and light steady between your last frame and this image and change one clear state. Each side must be between 300 and 6000 pixels.
Lock camera
Off by default. Switched on, the camera is held still during the new segment so that only the subject moves, which suits a source that was shot locked off. Leave it off when the shot needs a push, pan or tilt. No effect on what you are billed.
Seed
0 to 2147483647. Hold it steady to compare one changed field at a time; drop it for variety. It is a comparison tool, not a promise of frame-identical repeats. no lower than 0 · no higher than 2147483647

Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

1 required field missing: Input video

Output

Ready for a new run

Your result will appear here.

Configure the inputs, review the estimate, then run the model.

{
  "model": "bytedance/seedance-1.5-pro-spicy/video-extend",
  "input": {
    "duration_seconds": 5,
    "resolution": "720p",
    "generate_audio": true,
    "camera_fixed": false,
    "prompt": "Continue the scene naturally, keeping the same subject, camera movement and lighting."
  }
}

Introduction

Seedance 1.5 Pro Spicy Video extend continues a clip you already have. Send it as video_url; a prompt is optional. The final frame of your clip becomes the opening frame of a new Seedance 1.5 Pro Spicy image-to-video shot of 4 to 12 seconds, and the two are joined into one MP4: your original first, then the continuation, with the repeated seam frame removed. The new segment also comes back as its own file, so you can keep extending or edit the pieces separately.

Key features & highlights

Continuity comes from the last frame. Wardrobe, set, light and where everyone stands carry over because the new segment literally starts on your final frame. Motion does not carry over the same way: the model sees one still, not the whole clip, so describe the movement you want to continue instead of assuming it will keep its speed or direction.

One file back, plus the new piece on its own. The joined file keeps your clip’s frame rate and its framing, with no black bars, and is encoded as H.264 MP4 with AAC sound. To line the seam up, the picture may be trimmed or adjusted by a few percent at the edges. If the model returns a noticeably different shape, the new segment is scaled to fill your frame and centered, cropping what spills over. Sound from your source stays; sound generated for the new segment follows it; a silent side is padded with silence so picture and sound stay in step at the seam. The second asset in the output is the new segment alone, ready for another extend or for an editor.

Camera lock is available. Turn on camera_fixed and the frame holds still while the subject keeps moving, which matches a source that was shot locked off.

Everything else is Seedance 1.5 Pro Spicy image-to-video. The new segment runs on the same route, with the same content range and the same per-second price as the image-to-video endpoint, and a failed generation is refunded the same way. If the generation succeeds but the join itself cannot be built, the task fails and the charge is refunded.

Request parameters

Request parameters for Seedance 1.5 Pro Spicy · Video Extend
Parameter	Required	Description
`prompt`	No	Optional. What happens next: the action that follows, the camera move and the sound.
`last_image_url`	No	Optional target closing frame: the new segment lands on this picture, for a transition or a loop back to a known image.
`duration_seconds`	No	Length of the new segment in whole seconds, 4 to 12, default 5, and the billed quantity. Your source is added on top and is not billed. `≥ 4` · `≤ 12` · Default: `5`
`resolution`	No	Resolution of the new segment: 480p / 720p / 1080p, default 720p. Match your source: it only sets the quality of the new segment. `480p` · `720p` · `1080p` · Default: `720p`
`generate_audio`	No	On by default, so the new segment comes with generated sound. Your source keeps its own sound either way; when one side is silent, the joined file is padded with silence. Default: `true`
`camera_fixed`	No	Off by default. Switched on, the camera is held still during the new segment so that only the subject moves, which suits a source that was shot locked off. Default: `false`
`seed`	No	0 to 2147483647. Hold it steady to compare one changed field at a time; drop it for variety. `≥ 0` · `≤ 2147483647`
`video_url`	Yes	The clip to continue: MP4, MOV or WebM, up to 60 seconds. Its final frame becomes the opening frame of the new segment, so cut it on a clean, sharp frame. at least 1 characters

Pricing

Billed per second of the new segment, at the resolution and sound setting you choose; the source clip you send is not billed.

Pricing
Resolution	Generate audio: No	Generate audio: Yes
`480p`	$0.012 / second	$0.024 / second
`720p`	$0.026 / second	$0.052 / second
`1080p`	$0.052 / second	$0.104 / second

Use cases

Lengthen a shot that ended too early, such as a product turntable that stops before the label faces camera, or a walk that cuts before the subject reaches the door. Extend it by a few seconds and describe only the remaining motion.

Build a longer sequence step by step. Generate a first shot, extend it, then extend the joined result again; each step bills only the seconds it adds. Because every step starts from a single frame, watch each seam before stacking the next one.

Prompt guide & pro tips

Describe the next beat, not the whole scene. The frame already fixes who and where, so spend the prompt on the action that follows, the camera move and the sound. Repeat the camera language your clip ended on, such as a slow push in or a locked shot, so the seam reads as one take.

Trim before you extend. The last frame is the only thing the model sees, so a blurred, mid-cut or heavily compressed ending carries straight into the continuation. Cut your source on a clean, sharp frame first. Sources of up to 60 seconds are accepted as MP4, MOV or WebM.

Keep the resolution consistent. Pick the resolution of your source clip, and set duration_seconds to the length you actually need: the charge follows the new segment only. The framing of the new segment follows the last frame of your clip, so there is no aspect ratio to choose; expect a close match to the source, not a pixel-exact one.

API quick start

# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $SPICY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
  -d '{
  "model": "bytedance/seedance-1.5-pro-spicy/video-extend",
  "input": {
    "duration_seconds": 5,
    "generate_audio": true,
    "resolution": "720p",
    "video_url": "https://example.com/reference.mp4"
  }
}'

# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $SPICY_API_KEY"

See the API reference for authentication, the complete schema, polling, and error handling.

Related models and next tasks

Missing the model you need?

Tell us what to add and where you would use it. Requests go to the people who decide what gets onboarded next.

These previews show selected examples. Try your own prompt and settings in the Playground.

UNCENSORED LOCKED-SHOT API

Uncensored, and the camera holds absolutely still.

Key numbers

Camera control: LOCK; camera_fixed holds the frame still; no other spicy family publishes it.
Clip length: 4–12S; duration_seconds takes whole seconds from 4 to 12; the default is 5.
Top resolution: 1080P; 480p, 720p and 1080p. There is no 4k tier on this generation.
Prompt: OPTIONAL; prompt is not required — send image_url alone and the frame still moves.
Repeatable runs: SEED; seed accepts 0 to 2147483647, so one changed word can be judged on its own.
Sound included: AUDIO; generate_audio is on by default and renders sound against the picture.

What it does

Stillness as a control

A locked frame lets a small movement carry the clip

Set camera_fixed true and the frame stops dead while the subject keeps moving inside it. Close, unhurried footage is where that pays: a wandering camera turns a held look into a music video, while a locked frame lets a breath, a shifted ankle or a hand on a duvet carry the whole clip. No other spicy family offers the switch.

The frame is the brief

What the still shows is already in the clip

image_url is the only required field. Wardrobe, pose, skin and the exposure all arrive with the picture before the prompt is read, which is why frame-driven work survives briefs that a blank page will not. With the camera locked as well, the composition you approved is the composition you receive.

Know the ceiling

1080p and twelve seconds are hard limits

This generation stops at 1080p and twelve seconds, and offers no reference endpoint. Those are real limits, not defaults you can raise. If a shot needs 4K or thirty seconds, the 2.5 Spicy family goes there — but it will not hold the camera still for you, and that trade is the whole reason to be on this page.

Before you spend

image-to-video

This is the literal path, and the one to use when a prompt-only route gets refused: whatever the opening frame contains is already in the clip. Three boundaries to know before spending anything. last_image_url is accepted only alongside image_url and never on its own. This generation stops at 1080p and twelve seconds. And Seedance's own safety layer still runs in front of generation even here — kissing wording comes back rejected before a frame renders, while the same beat framed as a whisper at the ear or foreheads touching passes. Put the action in the frame rather than in the sentence, or take that shot to a Wan family, which accepts the wording Seedance refuses.

all

Uncensored means we do not review your generations; it does not move responsibility. Adults only, licensed material, documented consent, no non-consensual imagery, no impersonation of a real person. Generated files are kept for 14 days, so copy anything you intend to keep into your own storage.

Where it fits

First-person and point-of-view clips
Feet at the end of a bed, a hand on a duvet, a look held straight down the lens: shots that only work when the camera behaves like a person lying still. camera_fixed is what makes that possible rather than approximate.
Footage other platforms refuse
First-person framing, couples of any gender, roleplay: none of it is reviewed on our side. Put the content in the opening frame and the model animates what the picture actually shows rather than what a sentence asked for.
Loops that do not drift
A locked frame and a small movement return close to where they started, so the clip cuts into a loop without a visible jump. Send the same still as image_url and last_image_url and keep the motion to a breath or a shift of weight.
A client change without a reshoot
Pin the seed on an approved take, change one clause — the hand moves left instead of right, the light warms — and re-run. Because the camera is locked and the frame is fixed, the second version is recognisably the same shot rather than a new one.

Model reference

Seedance 1.5 Pro Spicy API reference

Seedance 1.5 Pro Spicy API specifications

Endpoint: image-to-video and video-extend
Required input: image_url; prompt is optional
Clip length: 4–12 whole seconds, default 5
Resolution: 480p, 720p (default), 1080p — no 4k on this generation
Camera: camera_fixed locks the frame; false by default
Aspect ratio: adaptive (default), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Content review: None on our side; the model's own refusals still apply

How to call the Seedance 1.5 Pro Spicy API

1. Compose the opening frame as a locked shot
Frame it the way you want the whole clip framed, because with camera_fixed set that is exactly what you get. The still on this page came from a text-to-image family in this same catalogue, composed high-key and wide so the subject has room to move without the camera helping.
2. Describe movement inside the frame
The clip on this page came from the still beside it and exactly this prompt: “Camera stays locked off. Her crossed ankles rock slowly, one foot flexing, her fingers trace a circle on the duvet and her chest rises with a long breath. Nothing else in frame moves except the light shifting on the sheets.” Five seconds, 720p, camera_fixed true. Every verb belongs to the subject, never to the camera.
3. Pin the seed, then change one clause
Send an Idempotency-Key, keep the task id, and poll or take the callback. Once a take is right, pin its seed and edit a single phrase per run — with the camera locked and the frame fixed, the difference you get back belongs to that phrase rather than to a new draw. It stays a controlled comparison, not a frame-identical repeat.

The short version

Seedance 1.5 Pro Spicy is the uncensored member of ByteDance's Seedance 1.5 Pro generation, published here as an image-to-video API plus a video-extend API. Send image_url and you get 4 to 12 seconds back at 480p, 720p or 1080p, in six aspect ratios or adaptive, with a native soundtrack generated alongside the frames unless generate_audio is off. The prompt is optional, last_image_url gives the shot a defined ending or a clean loop, and seed makes two runs comparable. What no other uncensored family here offers is camera_fixed, which holds the frame absolutely still while the subject moves inside it. Billing is per second of generated video. We do not review what you generate; rights and consent stay yours.