docs(generate): add Seedance 2.5 as a distinct pick, not a newer default

Seedance 2.5 reads like a successor to 2.0 and is not one. Checked against the
live contracts:

  seedance_2_0  resolution 480p/720p/1080p/4k   mode std|fast
  seedance_2_5  resolution 480p/720p            mode t2v|omni_reference|
                                                     video_edit|video_extension

2.5 is reference-driven generation, video editing and extension at up to 720p.
Making it the default would silently downgrade every 4K brief, so 2.0 stays the
default for serious motion and 2.5 is routed by what it is FOR.

Flag tables list 2.5 only where it declares the parameter — image, video and
audio references. It has no start/end-image, so it is absent from those rows.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Author: nurdabolatov

higgsfield-generate/SKILL.md

@@ -103,6 +103,7 @@ If the user says "analyze this video", "score this ad", "evaluate the hook", or
    - Fast batch / volume → Veo 3.1 Lite
    - Bold/stylized image-to-video from a required start image → Grok Video 1.5 (`grok_video_v15`). Requires one `--start-image` or `--image`, duration 2–15s, resolution `480p` or `720p`.
    - Multimodal reference-to-video with up to 7 images or one video reference → Gemini Omni Flash (`gemini_omni`); keep Seedance 2.0 as the default serious-video pick.
+   - Reference-driven generation, editing an existing video, or extending one → **Seedance 2.5** (`seedance_2_5`), whose modes are `t2v` / `omni_reference` / `video_edit` / `video_extension` and which takes image/video/audio reference arrays. It is NOT a newer Seedance 2.0: it caps at **720p**, so anything needing 1080p or 4K stays on Seedance 2.0.
 
    **Video analysis:**
    - Rate a finished video's hook, virality potential, attention, retention, or distraction risk → Virality Predictor (`brain_activity`). This is a video analysis model that returns a text score/report, not a generated media asset.
@@ -131,11 +132,11 @@ For workflow jobs, use `higgsfield generate workflow <workflow_name> ... --wait`
 
 | Flag | Purpose | Models that accept it |
 |---|---|---|
-| `--image <path-or-id>` | reference image | most image models, `grok_video_v15`, `multi_image_to_3d`, `seedance_2_0`, `veo3`, `marketing_studio_video` |
+| `--image <path-or-id>` | reference image | most image models, `grok_video_v15`, `multi_image_to_3d`, `seedance_2_0`, `seedance_2_5`, `veo3`, `marketing_studio_video` |
 | `--start-image <path-or-id>` | first frame for image-to-video transitions | `grok_video_v15`, `kling3_0`, `kling3_0_turbo`, `kling2_6`, `veo3_1`, `seedance_2_0`, `marketing_studio_video` |
 | `--end-image <path-or-id>` | last frame for transitions | `kling3_0`, `seedance_2_0`, `marketing_studio_video` |
-| `--video <path-or-id>` | reference or analyzed video | `seedance_2_0`, `brain_activity` |
-| `--audio <path-or-id>` | reference audio (lipsync, soundtrack match) | `seedance_2_0` (use this, NOT `--generate-audio`) |
+| `--video <path-or-id>` | reference or analyzed video | `seedance_2_0`, `seedance_2_5`, `brain_activity` |
+| `--audio <path-or-id>` | reference audio (lipsync, soundtrack match) | `seedance_2_0`, `seedance_2_5` (use this, NOT `--generate-audio`) |
 
 For reference-array models, the explicit flags are `--image-references`, `--video-references`, and `--audio-references`; `--image`, `--video`, and `--audio` are short aliases when the schema exposes those params.
 

higgsfield-generate/references/model-catalog.md

@@ -44,6 +44,7 @@ Preferred defaults for examples and quick-start guidance in this repo:
 |---|---|---|
 | Gemini Omni Flash | Google | **Fast multimodal reference-to-video.** Use for prompt-guided video generation from image references and optionally one video reference, especially when the brief benefits from Google's Gemini/Veo-style understanding without making it the default over Seedance 2.0. |
 | Seedance 2.0 | Bytedance | **SOTA all-purpose video up to 4K.** Crisp, consistent identity, multi-shot capable. The default for any serious motion / cinematic / production brief. |
+| Seedance 2.5 | Bytedance | **Reference-driven video, editing and extension.** Modes `t2v` / `omni_reference` / `video_edit` / `video_extension`, with image/video/audio reference arrays. A different tool from Seedance 2.0, not a newer one — it caps at **720p**, so 1080p/4K work stays on 2.0. |
 | Kling 3.0 | Kling | **Cheaper Seedance 2.0 substitute** for single-plane scenes that don't need heavy motion. Multi-shot, audio sync, motion transfer. |
 | Kling 3.0 Turbo | Kling | **Fast Kling option for simple motion.** Text-to-video and single start-frame animation when the user explicitly wants speed, lower cost, or a quick Kling 3.0 variant. |
 | Seedance 1.5 Pro | Bytedance | A budget-friendly Seedance for clean single-take shots. |