Troubleshooting and Reference

Model Capability Matrix

View as Markdown

This matrix is the dense reference for the video models shown in ChatCut’s current selector. Recheck the visible Video settings before sending because provider and rollout limits can change.

ModelGenerate inputsReference limitsEditExtendOutput tiers
Seedance 2.5Text, first frame, first + last frame, or referencesUp to 30 images, 10 videos, and 10 audio filesOne 4–30s source video plus an edit promptOne source video plus an extension prompt480p, 720p, 1080p, or native 4K
Seedance 2.5 FlashSame input structure as Seedance 2.5Up to 10 images, 5 videos, and 5 audio filesOne 4–30s source video plus an edit promptOne source video plus an extension prompt480p, 720p
Seedance 2.0Text, first frame, first + last frame, or referencesUp to 9 images, 3 videos, and 3 audio files (9 files total in Video Gen); audio needs an image or videoNoNo480p, 720p, 1080p, or native 4K
Seedance 2.0 FastSame input structure as Seedance 2.0Same limits as Seedance 2.0NoNo480p, 720p
Seedance 2.0 miniSame input structure as Seedance 2.0Same limits as Seedance 2.0NoNo480p, 720p
Gemini OmniText, first frame, first + last frame, or up to 3 image referencesImage inputs onlyOne project-library video up to about 10sOne project-library video up to about 10s plus an extension prompt360p, 720p, 1080p, or 4K (1080p and 4K are upscaled)
MiniMax H3Text, first frame, last frame, first + last frame, or referencesUp to 9 images, 3 videos, and 3 audio files; 12 files totalNoNo768p or 2K
MiniMax H3 MaxText, first frame, or first + last frameNo reference media; a last frame requires a first frameNoNo480p or 768p
Kling 3.0Text, first frame, last frame, first + last frame, or reference images; frames and images combineUp to 7 images in all, frames included; no reference video or audioNoNo720p or 1080p
Kling 4.0Text, first frame, last frame, first + last frame, or references; frames and references combineUp to 10 images in all, frames included, plus up to 5 videos (3–30s each, 30s total); no audioNoNo720p or 1080p
Kling 4.0 FlashSame input structure as Kling 4.0Up to 10 images in all, frames included, plus up to 5 videos (3–20s each, 20s total); no audioNoNo720p

Rules to remember:

  • A last frame requires a first frame, except on MiniMax H3, Kling 4.0, and Kling 3.0 without reference images.
  • Gemini Omni first-frame and multi-image-reference modes are mutually exclusive.
  • Seedance 2.5 Edit and Extend are distinct modes with their own source slots.
  • MiniMax H3 frame inputs and multimodal references are mutually exclusive.
  • Seedance 2.0 and Seedance 2.5 offer native 4K. 4K clips take noticeably longer and cost about twice as much as 1080p on Seedance 2.0, and about 1.6 times as much on Seedance 2.5. Seedance 2.5 Flash, Seedance 2.0 Fast, and Seedance 2.0 mini stop at 720p. Gemini Omni’s 1080p and 4K are upscaled.
  • MiniMax H3 Max always requires a prompt and does not support reference media, editing, extension, or 2K output.
  • Kling 3.0 makes 3–15s clips in whole seconds at 16:9, 9:16, or 1:1; with frames and no reference images, the output follows the frame image. Its prompt is limited to 2,500 characters and has no negative prompt, so write exclusions into the prompt.
  • Kling 4.0 makes clips of 3–30s at 21:9, 16:9, 9:16, or 1:1; frames make the ratio follow the input, and text-only clips default to 16:9. Reference images must be JPG or PNG, at least 300 px per side, with a width:height ratio between 2:5 and 5:2. Reference videos must be MP4 or MOV, 700–4553 px per side, at 24–60 fps; they guide motion, style, or characters, and the output is a new 24 fps clip. The prompt can run up to 26,000 English characters or 11,000 in other languages. Refer to inputs in the prompt as @first_frame, @last_frame, @image_1, @image_2, @video_1, and so on.
  • Kling 4.0 Flash takes the same inputs as Kling 4.0 but makes 3–20s clips at 720p only, and its reference videos can total 20s.
  • Kling 3.0, Kling 4.0, and Kling 4.0 Flash always generate native audio and take no audio references; describe dialogue, sound effects, and music in the prompt.
  • Switching model or mode can remove incompatible attachments.
  • The selected duration, resolution, and supported video inputs affect the credit estimate.

For model selection, media inputs, and the exact controls to use, see AI Video Generation.