MiniMax H3 Open Weights Image to Video animates a first-frame image, optionally with last-frame guidance, into coherent 480P / 540P / 768P videos with native stereo audio, 5-15 second duration, flexible aspect ratios, and per-second billing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.125per run·~80 / $10
The waiter sets the coffee down and says with a smile: "Your cappuccino, exactly how you like it." The woman looks up and replies: "You remembered. Thank you." Seaside cafe ambience.
MiniMax H3 Image-to-Video LoRA Open Weights runs the open-weights edition of MiniMax H3 with LoRA support on WaveSpeedAI. This endpoint is separate from the official minimax/h3 API and uses its own 480p / 768p / 1080p resolution options and per-second pricing.
MiniMax H3 generates video and native stereo audio in a single pass. Provide a first-frame image plus a prompt, and the model animates the scene with synchronized dialogue, sound effects, music, or ambience. You can also provide an optional last_image to guide the ending frame.
Open-weights MiniMax H3 workflow
Use the open-weights edition of MiniMax H3 through WaveSpeedAI-hosted infrastructure.
Image-to-video generation
Animate a first-frame image into a complete video with prompt-guided motion.
Native stereo audio
Generate visuals and synchronized stereo audio together in one pass.
Optional last-frame control
Use last_image to guide the final frame and create a controlled start-to-end transition.
LoRA support
Load up to 3 LoRA weights per request, each with its own scale.
Prompt-controlled soundtrack
Use an Audio: line in the prompt to guide music, dialogue, ambience, and sound effects.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Desired motion, camera movement, timing, and an Audio: line for soundtrack guidance. |
| image | Yes | First-frame image URL. The output canvas follows this image's aspect ratio. |
| last_image | No | Optional last-frame image URL. When provided, the model generates motion from the first frame toward this ending frame. |
| resolution | No | Output resolution: 480p, 540p, 768p, or 1080p. Default: 480p. |
| duration | No | Output duration in seconds. Range: 3–15. Default: 5. |
| seed | No | Fixed seed for reproducible output. |
| loras | No | Up to 3 LoRA weights. Each item uses {path, scale}, where path is a LoRA file URL. |
last_image when you want to control the final frame or ending direction.480p for lower-cost generation, 540p for a mid-price step up, 768p for higher-resolution output, or 1080p for full-HD output.3 to 15 seconds.Pricing is based on generated video duration and selected resolution.
| Resolution | Per second | 5s | 15s |
|---|---|---|---|
| 480p | $0.05 | $0.25 | $0.75 |
| 540p | $0.075 | $0.375 | $1.125 |
| 768p | $0.10 | $0.50 | $1.50 |
| 1080p | $0.20 | $1.00 | $3.00 |
Duration is capped at 15 seconds for pricing. LoRA loading does not add a separate charge.
image and last_image to guide both the opening and ending of the video.last_image when the final pose, composition, or ending beat matters.Audio: line to guide soundtrack, ambience, voice, and effects.seed when comparing LoRA scale or prompt changes.scale around 0.8–1.0, then adjust based on the strength of the LoRA effect.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-to-video-lora with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Minimax H3 Image To Video Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "480p",
"duration": 5
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-to-video-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-to-video-lora";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "480p",
"duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "480p",
"duration": 5
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-to-video-lora", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Minimax H3 Image To Video Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. MiniMax H3 Open Weights Image to Video animates a first-frame image, optionally with last-frame guidance, into coherent 480P / 540P / 768P videos with native stereo audio, 5-15 second duration, flexible aspect ratios, and per-second billing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/minimax-h3-image-to-video-lora.
Minimax H3 Image To Video Lora starts at $0.25 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `resolution`, `duration`, `seed`, `last_image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/minimax-h3-image-to-video-lora.
Median end-to-end generation time on WaveSpeedAI is around 37 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.