zlei6/OpenMontage
1
0
Fork 0
mirror of https://github.com/calesthio/OpenMontage.git synced 2026-08-24 17:10:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into codex/add-gemini-seedance-minimax-models

Browse Source 
# Conflicts:
#	docs/PROVIDERS.md
This commit is contained in:
calesthio
2026-08-13 12:48:49 -07:00
parent 8cdd37f523 494a95e62a
commit 9e43f90e2b
14 changed files with 2354 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/ARCHITECTURE.md
View File

@@ -145,6 +145,7 @@ Three selector tools abstract multi-provider capabilities:
| `tts_selector` | Text-to-speech | Ranks discovered providers by task fit, quality, control, reliability, cost, latency, and continuity |
| `image_selector` | Image generation | Ranks discovered providers from the live registry; no hardcoded provider order |
| `video_selector` | Video generation | Ranks discovered providers from the live registry; user preference is respected when explicitly provided |
| `atlas_image` / `atlas_video` | Atlas Cloud generation | Exposes exact per-model route catalogs for image generation/editing and text/image/reference/video-edit generation |
Selectors route based on: user preference when explicitly set, then scored ranking across available providers. They adapt input schemas between providers transparently.

28
docs/PROVIDERS.md
View File

@@ -54,6 +54,7 @@ AZURE_SPEECH_REGION= # Speech resource region, e.g. eastus
# MULTI-MODEL GATEWAY (one key, 6+ tools)
FAL_KEY= # FLUX, Recraft, Kling, Veo, MiniMax video
MINIMAX_API_KEY= # MiniMax first-party image + MiniMax H3 video generation
ATLASCLOUD_API_KEY= # Atlas Cloud image/video gateway
# KLING OFFICIAL DIRECT API
KLING_API_KEY= # Official Kling video, image, TTS, avatar, lip sync
@@ -403,6 +404,32 @@ choose them with `preferred_provider: "minimax"`.
---
### Atlas Cloud — Image and Video Gateway
**Tools:** `atlas_image`, `atlas_video`
**Env var:** `ATLASCLOUD_API_KEY` (aliases: `ATLAS_CLOUD_API_KEY`, `ATLAS_API_KEY`)
**Skill:** `.agents/skills/atlas-cloud/SKILL.md`
Atlas Cloud provides one endpoint and key for the following explicitly cataloged
routes. OpenMontage validates each model's real schema instead of treating task
suffixes or parameter names as interchangeable.
| Family | Supported routes | Current Atlas rate |
|---|---|---:|
| Seedance 2.5 | text/image/reference to video | $0.134/sec |
| Seedance 2.0 | text/image/reference to video | $0.112/sec |
| Gemini Omni Flash | text/image/reference to video; video edit; developer text/image/reference | $0.112–0.140/sec |
| MiniMax H3 | text/image/reference to video | $0.100/sec |
| Seedream 5.0 Pro | text to image; edit; layer decomposition | $0.022–0.045/image |
| GPT Image 2 | text to image; edit | $0.009–0.010/image |
| Nano Banana 2 | text to image; edit | $0.080/image |
Inspect `get_info()["model_catalog"]` for exact IDs, operations, media shapes,
durations, and resolutions. Prices are estimates sourced from each model's
machine-readable Atlas page and should be reconfirmed before a paid batch.
---
### Kling Official — Direct API
> **Official Kling path.** This is separate from `kling_video` via fal.ai: it uses Kling's official `Authorization: Bearer <KLING_API_KEY>` API, provider name `kling_official`, and direct Classic/Turbo/Omni task protocols.
@@ -1330,6 +1357,7 @@ These tools require only FFmpeg or Python packages — no GPU, no API key.
| **ElevenLabs** | `ELEVENLABS_API_KEY` | `elevenlabs_tts`, `music_gen` | Free tier + paid |
| **fish.audio** | `FISH_AUDIO_API_KEY` | `fish_audio_tts` | Free tier (s2.1-pro-free) + paid |
| **fal.ai** | `FAL_KEY` | `flux_image`, `recraft_image`, `kling_video`, `veo_video`, `seedance_video`, `gemini_omni_fal`, `minimax_fal_video` | Pay-as-you-go |
| **Atlas Cloud** | `ATLASCLOUD_API_KEY` | `atlas_image`, `atlas_video` | Pay-as-you-go |
| **Kling Official** | `KLING_API_KEY` | `kling_official_video`, `kling_official_image`, `kling_tts`, `kling_avatar`, `kling_lip_sync` | Pay-as-you-go |
| **Volcengine Ark** | `ARK_API_KEY` | `seedance_ark` | Pay-as-you-go |
| **MiniMax direct** | `MINIMAX_API_KEY` | `minimax_image`, `minimax_video` | Pay-as-you-go |