ai-video-gen

Name: ai-video-gen
Author: calesthio

413installs4.9kforks

How to install ai-video-gen?

calesthio/openmontage/ai-video-gen

$npx -y skills add calesthio/OpenMontage --skill ai-video-gen

Installs into the current project.

Summary

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation

Files · 1

View on GitHub

SKILL.md

1	# Video Generation (Multi-Gateway)
2
3	Generate AI videos from text prompts. Supports multiple providers via four API paths:
4
5	\| Gateway \| Env Variable \| Providers \| Tool \|
6	\|---------\|-------------\|-----------\|------\|
7	\| fal.ai \| `FAL_KEY` \| Seedance 2.0 (standard + fast), Kling v3/v2.1, MiniMax, VEO \| `seedance_video`, `kling_video`, `minimax_video`, `veo_video` \|
8	\| HeyGen \| `HEYGEN_API_KEY` \| VEO 3.1, Kling Pro, Sora v2, Runway Gen-4, Seedance Pro / Lite (1.x) \| `heygen_video` \|
9	\| Kling Official \| `KLING_API_KEY` \| Kling official Classic, Turbo, and basic Omni video \| `kling_official_video` \|
10	\| Gemini API \| `GEMINI_API_KEY` / `GOOGLE_API_KEY` \| Gemini Omni Flash (generation + conversational editing) \| `gemini_omni_video` \|
11
12	Iterative editing — Gemini Omni. When the brief calls for refining an existing clip (add/remove objects, restyle, change lighting or on-screen text) rather than regenerating, Gemini Omni Flash is the only provider in the fleet with stateful multi-turn editing. See Layer 3 `gemini-omni` for the authoritative prompting guide (reference-image tags, timecode syntax, edit-prompt rules) before writing any prompt for it.
13
14	Preferred premium default — Seedance 2.0. When any premium gateway is configured (`FAL_KEY` → `seedance_video`, or HeyGen's Video Agent / Avatar Shots path), Seedance 2.0 is the preferred default for cinematic, trailer, and high-fidelity clip work. It is the only model in the fleet with single-pass native synchronized audio, multi-shot generation, director-level camera control, and lip-sync from quoted dialogue, and it ranks #1 on Artificial Analysis Elo as of early 2026. Switch off it only when the user has a specific reason (budget, provider preference, stylistic fit like VEO for photoreal landscape or Kling for specific anime look). See Layer 3 `seedance-2-0` for the authoritative prompting and parameter guide.
15
16	IMPORTANT: Always use `video_selector` instead of calling provider tools directly. The selector handles availability checks, cost comparison, and automatic fallback, and its scoring engine already biases toward Seedance 2.0 for cinematic intent.
17
18	## Authentication
19
20	Use whichever configured gateway best matches the user's available providers and cost/quality goals.
21
22	- HeyGen: Set `HEYGEN_API_KEY` to access the multi-model gateway.
23	- fal.ai: Set `FAL_KEY` to access Kling, MiniMax, and Veo through fal.ai.
24	- Kling Official: Set `KLING_API_KEY` to access Kling's official direct API via `provider="kling_official"`.
25	- Gemini API: Set `GEMINI_API_KEY` or `GOOGLE_API_KEY` to access Gemini Omni video generation and conversational editing.
26
27	Do not describe any gateway as the default or top choice without checking the registry and current task fit first.
28
29	fal.ai Kling (`kling_video`, `provider="kling"`) and Kling Official (`kling_official_video`, `provider="kling_official"`) are different paths. Do not reuse fal.ai queue URLs, `FAL_KEY`, or image upload behavior when the official provider is selected.
30
31	```bash
32	curl -X POST "https://api.heygen.com/v1/workflows/executions" \
33	-H "X-Api-Key: $HEYGEN_API_KEY" \
34	-H "Content-Type: application/json" \
35	-d '{"workflow_type": "GenerateVideoNode", "input": {"prompt": "A drone shot flying over a coastal city at sunset"}}'
36	```
37
38	## Default Workflow
39
40	1. Call `POST /v1/workflows/executions` with `workflow_type: "GenerateVideoNode"` and your prompt
41	2. Receive a `execution_id` in the response
42	3. Poll `GET /v1/workflows/executions/{id}` every 10 seconds until status is `completed`
43	4. Use the returned `video_url` from the output
44
45	## Execute Video Generation
46
47	### Endpoint
48
49	`POST https://api.heygen.com/v1/workflows/executions`
50
51	### Request Fields
52
53	\| Field \| Type \| Req \| Description \|
54	\|-------\|------\|:---:\|-------------\|
55	\| `workflow_type` \| string \| Y \| Must be `"GenerateVideoNode"` \|
56	\| `input.prompt` \| string \| Y \| Text description of the video to generate \|
57	\| `input.provider` \| string \| \| Video generation provider (default: `"veo_3_1"`). See Providers below. \|
58	\| `input.aspect_ratio` \| string \| \| Aspect ratio (default: `"16:9"`). Common values: `"16:9"`, `"9:16"`, `"1:1"` \|
59	\| `input.reference_image_url` \| string \| \| Reference image URL for image-to-video generation \|
60	\| `input.tail_image_url` \| string \| \|

People who liked this also viewed

6 picks

Type

ai-video-gen

413installs4.9kforks

View on GitHub

How to install ai-video-gen?

calesthio/openmontage/ai-video-gen

$npx -y skills add calesthio/OpenMontage --skill ai-video-gen

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Video Generation (Multi-Gateway)
2
3	Generate AI videos from text prompts. Supports multiple providers via four API paths:
4
5	\| Gateway \| Env Variable \| Providers \| Tool \|
6	\|---------\|-------------\|-----------\|------\|
7	\| fal.ai \| `FAL_KEY` \| Seedance 2.0 (standard + fast), Kling v3/v2.1, MiniMax, VEO \| `seedance_video`, `kling_video`, `minimax_video`, `veo_video` \|
8	\| HeyGen \| `HEYGEN_API_KEY` \| VEO 3.1, Kling Pro, Sora v2, Runway Gen-4, Seedance Pro / Lite (1.x) \| `heygen_video` \|
9	\| Kling Official \| `KLING_API_KEY` \| Kling official Classic, Turbo, and basic Omni video \| `kling_official_video` \|
10	\| Gemini API \| `GEMINI_API_KEY` / `GOOGLE_API_KEY` \| Gemini Omni Flash (generation + conversational editing) \| `gemini_omni_video` \|
11
12	Iterative editing — Gemini Omni. When the brief calls for refining an existing clip (add/remove objects, restyle, change lighting or on-screen text) rather than regenerating, Gemini Omni Flash is the only provider in the fleet with stateful multi-turn editing. See Layer 3 `gemini-omni` for the authoritative prompting guide (reference-image tags, timecode syntax, edit-prompt rules) before writing any prompt for it.
13
14	Preferred premium default — Seedance 2.0. When any premium gateway is configured (`FAL_KEY` → `seedance_video`, or HeyGen's Video Agent / Avatar Shots path), Seedance 2.0 is the preferred default for cinematic, trailer, and high-fidelity clip work. It is the only model in the fleet with single-pass native synchronized audio, multi-shot generation, director-level camera control, and lip-sync from quoted dialogue, and it ranks #1 on Artificial Analysis Elo as of early 2026. Switch off it only when the user has a specific reason (budget, provider preference, stylistic fit like VEO for photoreal landscape or Kling for specific anime look). See Layer 3 `seedance-2-0` for the authoritative prompting and parameter guide.
15
16	IMPORTANT: Always use `video_selector` instead of calling provider tools directly. The selector handles availability checks, cost comparison, and automatic fallback, and its scoring engine already biases toward Seedance 2.0 for cinematic intent.
17
18	## Authentication
19
20	Use whichever configured gateway best matches the user's available providers and cost/quality goals.
21
22	- HeyGen: Set `HEYGEN_API_KEY` to access the multi-model gateway.
23	- fal.ai: Set `FAL_KEY` to access Kling, MiniMax, and Veo through fal.ai.
24	- Kling Official: Set `KLING_API_KEY` to access Kling's official direct API via `provider="kling_official"`.
25	- Gemini API: Set `GEMINI_API_KEY` or `GOOGLE_API_KEY` to access Gemini Omni video generation and conversational editing.
26
27	Do not describe any gateway as the default or top choice without checking the registry and current task fit first.
28
29	fal.ai Kling (`kling_video`, `provider="kling"`) and Kling Official (`kling_official_video`, `provider="kling_official"`) are different paths. Do not reuse fal.ai queue URLs, `FAL_KEY`, or image upload behavior when the official provider is selected.
30
31	```bash
32	curl -X POST "https://api.heygen.com/v1/workflows/executions" \
33	-H "X-Api-Key: $HEYGEN_API_KEY" \
34	-H "Content-Type: application/json" \
35	-d '{"workflow_type": "GenerateVideoNode", "input": {"prompt": "A drone shot flying over a coastal city at sunset"}}'
36	```
37
38	## Default Workflow
39
40	1. Call `POST /v1/workflows/executions` with `workflow_type: "GenerateVideoNode"` and your prompt
41	2. Receive a `execution_id` in the response
42	3. Poll `GET /v1/workflows/executions/{id}` every 10 seconds until status is `completed`
43	4. Use the returned `video_url` from the output
44
45	## Execute Video Generation
46
47	### Endpoint
48
49	`POST https://api.heygen.com/v1/workflows/executions`
50
51	### Request Fields
52
53	\| Field \| Type \| Req \| Description \|
54	\|-------\|------\|:---:\|-------------\|
55	\| `workflow_type` \| string \| Y \| Must be `"GenerateVideoNode"` \|
56	\| `input.prompt` \| string \| Y \| Text description of the video to generate \|
57	\| `input.provider` \| string \| \| Video generation provider (default: `"veo_3_1"`). See Providers below. \|
58	\| `input.aspect_ratio` \| string \| \| Aspect ratio (default: `"16:9"`). Common values: `"16:9"`, `"9:16"`, `"1:1"` \|
59	\| `input.reference_image_url` \| string \| \| Reference image URL for image-to-video generation \|
60	\| `input.tail_image_url` \| string \| \|

People who liked this also viewed

6 picks

Type