Spicy Image-to-Video Collection API
Curated lineup of image-to-video endpoints optimized for unlimited, high-volume content generation — spans ByteDance Seedance 2.0 and 1.5 Pro, Alibaba Wan 2.7, 2.6, and 2.2, and Shengshu Vidu Q3, with LoRA customization and video-extend support on the Wan 2.2 line, all reachable through a single WaveSpeedAI API key.
Ten endpoints across five providers, tuned for scalable content workflows. Pick by speed (Seedance 2.0 Fast), fidelity (Seedance 2.0 Standard, Wan 2.7), motion style (Vidu Q3, Wan 2.6, Seedance 1.5 Pro), or customization needs (Wan 2.2 LoRA + video-extend) — same request shape across every endpoint, one billing account, one rate-limit envelope.
About the Spicy Image-to-Video Collection API
What Spicy Image-to-Video Collection does, how it fits in the WaveSpeedAI model lineup, and why teams reach for it.
Spicy Image-to-Video Collection is a video generation model from WaveSpeedAI, available through the WaveSpeedAI REST API. Curated lineup of image-to-video endpoints optimized for unlimited, high-volume content generation — spans ByteDance Seedance 2.0 and 1.5 Pro, Alibaba Wan 2.7, 2.6, and 2.2, and Shengshu Vidu Q3, with LoRA customization and video-extend support on the Wan 2.2 line, all reachable through a single WaveSpeedAI API key.
Ten endpoints across five providers, tuned for scalable content workflows. Pick by speed (Seedance 2.0 Fast), fidelity (Seedance 2.0 Standard, Wan 2.7), motion style (Vidu Q3, Wan 2.6, Seedance 1.5 Pro), or customization needs (Wan 2.2 LoRA + video-extend) — same request shape across every endpoint, one billing account, one rate-limit envelope.
The Spicy Image-to-Video Collection family on WaveSpeedAI ships 10 REST endpoints covering Image-To-Video, Lora-Support, Video-Extend workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Spicy Image-to-Video Collection through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
All Spicy Image-to-Video Collection API endpoints
10 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.

Image To Video Spicy
Vidu Q3 Image-to-Video Spicy generates unlimited high-quality videos from images with smooth animations and diverse motion, optimized for scalable content generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Image To Video Spicy
Seedance 1.5 Pro Spicy Image-to-Video generates unlimited high-quality cinematic clips from images, optimized for scalable content generation with smooth animations and stable aesthetics. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video Extend Lora
Extend clips into unlimited longer videos with WAN 2.2 Spicy, producing smooth animation and supporting custom LoRA weights. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video Extend
Extend short clips into unlimited, high-quality longer videos with smooth animation using WAN 2.2 Spicy. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Image To Video Lora
Generate AI videos with personalized styles using LoRA. Upload images and apply a trained style model to WAN 2.2 — create unique, stylized videos with consistent visual identity.

Image To Video
WAN 2.2 Spicy converts images into unlimited high-quality videos with smooth animations optimized for scalable content generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Image To Video Spicy
WAN 2.6 Spicy converts images into unlimited high-quality videos with smooth animations optimized for scalable content generation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Image To Video Spicy
Wan 2.7 Spicy Image to Video is a fast AI image-to-video generation model that converts images into high-quality videos with smooth animations optimized for scalable content generation. Ready-to-use REST inference API for animating images, social media clips, product videos, advertising creatives, creative storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.

Image To Video Spicy (Fast)
Seedance 2.0 Fast Spicy Image to Video is a fast AI image-to-video generation model that creates high-quality cinematic clips from images at faster speed and lower cost, optimized for scalable content generation with smooth animations and stable aesthetics. Ready-to-use REST inference API for animating images, social media clips, product videos, advertising creatives, visual storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.

Image To Video Spicy
Seedance 2.0 Spicy Image to Video is a fast AI image-to-video generation model that creates high-quality cinematic clips from images, optimized for scalable content generation with smooth animations and stable aesthetics. Ready-to-use REST inference API for animating images, social media clips, product videos, advertising creatives, visual storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.
See Spicy Image-to-Video Collection in action
Real outputs generated by the Spicy Image-to-Video Collection API. Hover any video to preview, click to open the full-size viewer.
How to use the Spicy Image-to-Video Collection API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/image-to-video-spicy. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from"queued" or"processing" to"completed".
- 4
Read the output URL
Once status is"completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Spicy Image-to-Video Collection variant you called.
What you can build with Spicy Image-to-Video Collection
Common workflows developers and creators use the Spicy Image-to-Video Collection API for.
High-volume image animation
Every endpoint in the collection is tuned for unlimited, scalable image-to-video generation. Same WaveSpeedAI API key reaches all ten, so you can pick by per-call cost, latency, or provider preference without re-architecting the integration.
Multi-provider failover
Routing the same prompt across five providers (ByteDance, Alibaba, Shengshu, plus WaveSpeedAI's Wan 2.2 line) means a temporary capacity hit at one provider doesn't block your pipeline. No per-vendor SDK or auth setup — one integration covers every endpoint.
Speed vs fidelity tier choice
bytedance/seedance-2.0-fast/image-to-video-spicy for prompt iteration; bytedance/seedance-2.0/image-to-video-spicy and alibaba/wan-2.7/image-to-video-spicy for delivery; bytedance/seedance-v1.5-pro/image-to-video-spicy when you need the 1.5 Pro motion profile. Switch endpoint URL only — request body stays identical.
Cinematic motion from a single still
bytedance/seedance-2.0/image-to-video-spicy animates a reference image with cinematic camera motion and lighting, preserving subject identity and composition from the first frame. Native audio synthesis runs in the same pass.
Smooth motion from Wan and Vidu
alibaba/wan-2.7/image-to-video-spicy, alibaba/wan-2.6/image-to-video-spicy, and vidu/q3/image-to-video-spicy ship smooth, naturally-paced motion tuned for shorter shots — useful when the Seedance cinematic look is too heavy for the target output.
LoRA customization on the Wan 2.2 line
wavespeed-ai/wan-2.2-spicy/image-to-video-lora and wavespeed-ai/wan-2.2-spicy/video-extend-lora accept LoRA checkpoints for style, character, or brand consistency across a production run — the only variants in the collection with native LoRA support.
Video-extend for longer sequences
wavespeed-ai/wan-2.2-spicy/video-extend and the LoRA companion continue an input video from its last frame, with chain-extending for arbitrarily long sequences. The only endpoints in the collection that handle continuation rather than only first-frame animation.
One API key, one billing account
WaveSpeedAI fronts all ten endpoints behind a single API key, single billing relationship, and one rate-limit envelope. No per-vendor onboarding, no separate quotas, no rewriting integration code to swap providers.
Tips for prompting Spicy Image-to-Video Collection
Practical advice for getting better outputs from Spicy Image-to-Video Collection — drawn from the patterns that work across video models in production pipelines.
Pick the right speed tier first
bytedance/seedance-2.0-fast/image-to-video-spicy for prompt iteration; bytedance/seedance-2.0/image-to-video-spicy and alibaba/wan-2.7/image-to-video-spicy for delivery. Same prompt format works across all ten endpoints — switch the URL only.
Use cinematic camera language with Seedance
Seedance endpoints respond strongly to director-level vocabulary: orbit, dolly-in, push-in, crane shot, handheld follow. Translates more directly than generic motion descriptions.
Wan and Vidu prefer naturally-paced prompts
alibaba/wan-2.7/image-to-video-spicy, alibaba/wan-2.6/image-to-video-spicy, and vidu/q3/image-to-video-spicy tune toward smooth, naturally-paced motion. Phrase prompts as "the subject does X" rather than as cinematic shot lists.
Apply LoRA on the Wan 2.2 line for consistency
wavespeed-ai/wan-2.2-spicy/image-to-video-lora and wavespeed-ai/wan-2.2-spicy/video-extend-lora are the only endpoints in the collection that accept LoRA checkpoints — use them when you need recurring style, character, or brand identity across a production run.
Use Wan 2.2 video-extend for longer sequences
wavespeed-ai/wan-2.2-spicy/video-extend continues an input clip from its last frame. Chain extends to build arbitrarily long sequences — the other nine endpoints only animate a single first frame.
Route the same prompt across providers for A/B
Identical request body across the ten endpoints lets you A/B route to compare cost, latency, and motion style without re-prompting. Useful for pipelines that need provider redundancy or want to pick the strongest output per shot.
Seedance ships native audio in the same pass
Seedance 2.0 endpoints generate audio alongside video. Wan and Vidu endpoints are video-only — pair with a separate audio model when your output needs sound.
Spicy Image-to-Video Collection API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| vidu/q3/image-to-video-spicy | image-to-video | $0.35 |
| bytedance/seedance-v1.5-pro/image-to-video-spicy | image-to-video | $0.26 |
| wavespeed-ai/wan-2.2-spicy/video-extend-lora | lora-support | $0.20 |
| wavespeed-ai/wan-2.2-spicy/video-extend | video-extend | $0.15 |
| wavespeed-ai/wan-2.2-spicy/image-to-video-lora | lora-support | $0.20 |
| wavespeed-ai/wan-2.2-spicy/image-to-video | image-to-video | $0.15 |
| alibaba/wan-2.6/image-to-video-spicy | image-to-video | $0.50 |
| alibaba/wan-2.7/image-to-video-spicy | image-to-video | $0.50 |
| bytedance/seedance-2.0-fast/image-to-video-spicy | image-to-video | $0.50 |
| bytedance/seedance-2.0/image-to-video-spicy | image-to-video | $0.60 |
Call the Spicy Image-to-Video Collection API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/image-to-video-spicy" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{}'
# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Read the output URL from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY
const result = await client.run("bytedance/seedance-2.0/image-to-video-spicy", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bytedance/seedance-2.0/image-to-video-spicy",
{}
)
print(output["outputs"][0]) # → URL of the generated outputSpicy Image-to-Video Collection vs alternatives
When to pick Spicy Image-to-Video Collection over similar models on WaveSpeedAI.
Spicy Image-to-Video Collection vs Direct provider APIs
Going direct to ByteDance, Alibaba, and Shengshu means three separate accounts, three billing relationships, three rate-limit envelopes, and provider-specific SDKs. WaveSpeedAI consolidates all ten endpoints behind one integration with a consistent request shape.
Spicy Image-to-Video Collection vs Single-model pipeline
Pinning a pipeline to one image-to-video model means no fallback when that provider has capacity issues and no easy A/B for cost. The collection ships ten interchangeable endpoints so you can route by cost, latency, or output style without rewriting downstream code.
Spicy Image-to-Video Collection vs Self-hosted inference
Self-hosting image-to-video models means GPU capacity planning, model-update tracking across four vendors, and DevOps coverage. WaveSpeedAI handles capacity, updates, and uptime — bill per generation, no idle GPU cost.
Spicy Image-to-Video Collection API — Frequently asked questions
Pricing, license, integration — common questions about running Spicy Image-to-Video Collection on WaveSpeedAI.
What is the Spicy Image-to-Video Collection API?
Spicy Image-to-Video Collection is a WaveSpeedAI video generation model exposed as a REST API on WaveSpeedAI. Curated lineup of image-to-video endpoints optimized for unlimited, high-volume content generation — spans ByteDance Seedance 2.0 and 1.5 Pro, Alibaba Wan 2.7, 2.6, and 2.2, and Shengshu Vidu Q3, with LoRA customization and video-extend support on the Wan 2.2 line, all reachable through a single WaveSpeedAI API key. You can call it programmatically or try it from the playground linked above.
How do I call the Spicy Image-to-Video Collection API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/image-to-video-spicy 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]. Full Python / Node.js / cURL examples are above.
How much does the Spicy Image-to-Video Collection API cost?
Spicy Image-to-Video Collection starts at $0.15 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Spicy Image-to-Video Collection variants are available?
WaveSpeedAI hosts 10 Spicy Image-to-Video Collection endpoints: vidu/q3/image-to-video-spicy, bytedance/seedance-v1.5-pro/image-to-video-spicy, wavespeed-ai/wan-2.2-spicy/video-extend-lora, wavespeed-ai/wan-2.2-spicy/video-extend, wavespeed-ai/wan-2.2-spicy/image-to-video-lora, wavespeed-ai/wan-2.2-spicy/image-to-video, alibaba/wan-2.6/image-to-video-spicy, alibaba/wan-2.7/image-to-video-spicy, and more. Each variant has its own playground page and pricing.
Can I use Spicy Image-to-Video Collection outputs commercially?
Commercial usage rights follow the WaveSpeedAI model license. Most WaveSpeedAI models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Spicy Image-to-Video Collection on WaveSpeedAI instead of going direct?
One API key + one billing account across Spicy Image-to-Video Collection AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below WaveSpeedAI's direct API.
About WaveSpeedAI
The team behind Spicy Image-to-Video Collection and the broader WaveSpeedAI model lineup on WaveSpeedAI.
WaveSpeedAI runs an inference platform that hosts 1,000+ AI models from every major provider — ByteDance, Google, OpenAI, Alibaba, Kuaishou, ElevenLabs, and dozens of independent labs — behind one API key, one billing account, and one rate-limit envelope. WaveSpeedAI also ships first-party models (Image / Video Upscalers, Watermark Removers, Animate, InfiniteTalk) tuned for production pipelines.
Start building with Spicy Image-to-Video Collection on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from WaveSpeedAI and every other provider.