Use Luma in Hermes Agent.
Luma Ray 3.2 modifies existing video with prompt-driven transformations that preserve spatial coherence and 3D scene structure. Send a source video URL and a text prompt describing the transformation — Luma re-renders the footage with atmospheric lighting, environmental detail, and physically consistent camera motion. Hermes Agent calls it through the RunAPI custom endpoint.
Use RunAPI to modify a video with Luma Ray 3.2.
Requirements:
- Read the API key from RUNAPI_API_KEY.
- Use the custom:runapi provider with base_url https://runapi.ai/v1.
- Call POST https://runapi.ai/api/v1/luma/modify_video
- Set model to "luma-modify-video".
- Set source_video_url to the URL of the video to transform.
- Set prompt to describe the desired transformation.
- The task is async. Poll the returned task_id until status is "completed".
- When done, read the modified video URL from the response output.
curl -X POST https://runapi.ai/api/v1/luma/modify_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "luma-modify-video",
"prompt": "Transform the scene into a foggy autumn morning with golden light filtering through trees",
"source_video_url": "https://example.com/park-walk.mp4"
}'
{
"task_id": "tsk_abc123",
"status": "pending",
"model": "luma-modify-video"
}
Use Luma in Hermes Agent in three steps
Configure RunAPI
Set RUNAPI_API_KEY in the environment where Hermes Agent runs. If you already added RunAPI as a custom:runapi provider, the same key handles Luma video modification requests.
export RUNAPI_API_KEY=runapi_xxx
Call Luma modify_video
Send a POST request to the modify_video endpoint with model set to luma-modify-video, the source_video_url pointing to your input footage, and a prompt describing the transformation. Hermes Agent can build and send this request through the custom:runapi provider.
POST /api/v1/luma/modify_video
Poll for the result
The endpoint returns a task_id immediately. Poll the task status endpoint until the status is completed, then read the output video URL from the response. Video modification typically takes 30-120 seconds depending on complexity.
GET /api/v1/luma/modify_video/tsk_abc123
Luma modify_video API parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. Use luma-modify-video. |
prompt |
string |
Required. Text description of the desired video transformation — style changes, lighting, atmosphere, or scene edits. |
source_video_url |
string |
Required. URL of the source video to modify. Must be a publicly accessible MP4 or MOV file. |
watermark |
boolean |
Optional. Whether to add a watermark to the output video. |
callback_url |
string |
Optional. Webhook URL that receives a POST when the task completes. |
What is Luma on Hermes Agent?
Luma Ray 3.2 (Dream Machine) re-renders existing video with prompt-driven transformations while maintaining 3D spatial coherence and physically consistent camera motion. Through the Hermes Agent custom:runapi provider, it handles atmospheric shifts, style transfers, and environmental edits on source footage. Users value it for cinematic-looking results and its fast, frictionless iteration loop.
Luma use cases
Concept reels and animated stills
Transform static concept art or rough footage into stylized motion pieces. Hermes Agent can generate a base video with Kling or Wan, then pass it to Luma for atmospheric re-rendering in one workflow.
Seasonal and brand content repurposing
Restyle existing video assets to match seasonal campaigns, new brand guidelines, or different market aesthetics without reshooting. Luma preserves the original composition while changing the visual treatment.
Abstract and surreal visual content
Apply surreal, painterly, or abstract transformations to source footage for creative projects, music visualizations, or experimental content where Luma's dreamlike rendering quality stands out.
Luma + Hermes Agent questions
Luma modify_video re-renders existing footage with prompt-driven changes — atmospheric shifts (fog, rain, golden hour), style transfers (cinematic, anime, noir), lighting overhauls, and environmental transformations. It preserves the original camera motion and spatial layout of the scene.
No. Luma Ray 3.2 only modifies the visual track of your source video. If the source has audio, Luma's output is video-only. Use a separate audio model like ElevenLabs or Suno through RunAPI to add sound after the visual transformation is complete.
Asynchronous. The create endpoint returns a task_id immediately. Poll the task status endpoint or provide a callback_url to receive a webhook when the modified video is ready. Typical processing time is 30-120 seconds.
Yes. A Hermes Agent workflow can generate a video with Kling or Wan, then pass the output URL as source_video_url to Luma modify_video for atmospheric re-rendering — all through the same custom:runapi provider and RUNAPI_API_KEY. Each step uses the same async polling pattern.
Luma preserves the original composition and spatial layout, including character positions and proportions. However, fine facial details can drift during heavy style transfers. For best character consistency, keep style changes moderate or use reference images to anchor key subjects.
Yes. Hermes Agent can chain Luma calls -- apply a style change first, then a scene modification, each building on the previous output. This enables complex multi-pass video editing within one workflow.
Hermes Agent general setup
Not configured yet? Start with the RunAPI setup guide for Hermes Agent.
Hermes Agent setup guide →Try Luma in Hermes Agent today.
Get a free RunAPI key, configure the custom:runapi provider, and start modifying video with Luma Ray 3.2 spatial-aware transformations.