Ltx 2.3 Spicy Image To Video LoRA

Ltx 2.3 Spicy Image To Video LoRA

Playground

LTX 2.3 Spicy LoRA Image to Video API turns a reference image and prompt into expressive AI videos using selectable LoRA presets, optional LoRA strength overrides, duration, and resolution controls. Run fast REST inference on WaveSpeedAI with no cold starts and affordable pricing.

Features

Ltx-2.3-spicy/image-to-video-lora

wavespeed-ai/ltx-2.3-spicy/image-to-video-lora uses the same audio-video generation pipeline as the base image-to-video endpoint, while adding a curated LoRA stack for stronger style, motion, and visual control. You can use the recommended preset or override individual LoRA strengths per request.

Why Choose This?

• Same base image-to-video workflow Uses the same core audio-video pipeline as the base image-to-video endpoint.

• Preset-based LoRA control Choose between original for lighter styling or tuned for the recommended LoRA stack.

• Per-LoRA override support Override individual LoRA strengths on top of the selected preset for more flexible control.

• Style, motion, and look control Fine-tune visual style, motion behavior, and overall output feel with a curated LoRA set.

• Unlimited creative flexibility Designed for users who want more direct control over the generation result.

Parameters

This endpoint supports all inputs from the base image-to-video endpoint, plus the following extra fields:

Available LoRA Keys

sulphur, sulphur_v1, vbvr, dreamly, synth, plora, singularity, omninft, omninft_bf16, better_motion, physics_v2, hardcut, transition

How to Use

1. Prepare your base image-to-video inputs — Use the same required inputs as the base image-to-video endpoint.
2. Choose a preset (optional) — Use tuned for the recommended LoRA stack or original for a lighter effect.
3. Set LoRA overrides (optional) — Pass a loras object to adjust individual LoRA strengths.
4. Submit — Generate the final video result with LoRA-enhanced control.

Pricing

Billing Rules

• Minimum charge: 5 seconds.
• Maximum billed duration: 20 seconds.
• 720p costs 5/3× the 480p price.
• 1080p costs 7/3× the 480p price.
• Billing is based on max(5, min(duration, 20)).

Best Use Cases

• Style-controlled image-to-video generation — Apply stronger visual styling on top of the base image-to-video workflow.
• Motion tuning — Use motion-focused LoRAs such as better_motion or physics_v2 to guide output behavior.
• Look-and-feel customization — Combine preset stacks and LoRA overrides to shape the final visual result.
• Creative experimentation — Try different LoRA combinations for varied output styles and motion characteristics.

Pro Tips

• Use preset = tuned for the recommended default behavior.
• Use preset = original when you want results closer to the base input style.
• Use the loras object to override only the LoRAs you want to adjust.
• Set a LoRA value to 0 if you want to disable that LoRA while keeping the rest of the preset unchanged.
• Start with a small number of LoRA overrides before stacking many changes together.

Notes

• This endpoint includes all base image-to-video inputs and adds preset and loras.
• Default preset is tuned.
• Default loras value is {}.
• Unknown LoRA keys are ignored.
• Each active LoRA adds approximately 0.5–0.8 seconds of extra runtime at 480p / 5s.
• In the worst case, using all 13 LoRAs may increase runtime by approximately 30% compared with using no LoRAs.
• Pass loras: {"omninft": 0} to fully disable that LoRA from the selected preset without changing the rest.
• By using this endpoint, you confirm that you have the right to generate the requested content under your jurisdiction.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3-spicy/image-to-video-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "preset": "tuned",
    "loras": [],
    "resolution": "480p",
    "duration": 5,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"