Camera fields: start and end frames
21 of the 24 models' docs cover start and end frames. Of those, the commonest reading is “First and last frame”, for 11. Every row pairs a reading with the opening line taken from that model's docs. As of 2026-09-25.
| Model | Reading | What the docs say |
|---|---|---|
| Adobe Firefly | First and last frame | A first and a last keyframe image can be uploaded as fixed points for the clip |
| Google Veo | First and last frame | A separate mode generates video from a first and a last frame |
| Grok Imagine | First frame only | Video is generated from text or from a still image |
| Higgsfield | None in the docs | Not described in the docs read (2026-09-25) |
| HunyuanVideo 1.5 | First frame only | Text-to-video and image-to-video in one framework |
| Kling AI | First and last frame | Start and end frames to video is supported in VIDEO 2.6 and 3.0 |
| Leonardo Motion 2.0 | First frame only | A start frame from an uploaded or generated image |
| LTX | Several keyframes | The model supports several keyframes, not only a first frame |
| LTX Studio | First frame only | Presets are applied to a clip made from a first-frame image on the LTXV model |
| Luma Dream Machine | First and last frame | Keyframes set a start image, an end image or both |
| Midjourney | First and last frame | The image is the starting frame; --end sets an ending frame and --loop makes the two the same |
| MiniMax Hailuo | First and last frame | A first-frame image, a last-frame image or both can be set |
| Moonvalley Marey | Several keyframes | Several reference images are placed on a timeline and the model makes the transitions |
| Open-Sora 2.0 | First frame only | Image-to-video from a prompt and a reference image |
| Pika | First and last frame | Pikaframes takes a first and a last frame as still images |
| PixVerse | First and last frame | A Transition endpoint generates video between a first and a last frame |
| Runway | Several keyframes | Image to video uses an input image; keyframes moved to an Animate Frames app |
| SceneMixer | None in the docs | Not described in the docs read (2026-09-25) |
| Seedance | N/A, docs unreadable | The API reference asked for a sign-in and showed no text on the day read |
| SkyReels | First and last frame | Start and end frame control is part of the diffusion forcing model's inference code |
| Sora | First frame only | An input image anchors the first frame; the prompt says what happens next |
| Step-Video-TI2V | First frame only | The image condition becomes the first frame of the generated video |
| Vidu | First and last frame | Two images set the start frame and the end frame |
| Wan | First and last frame | A separate image-to-video mode takes a first and a last frame |
Inclusion rule. All 24 models on the register. Order. Alphabetical by model name.
1What this field covers
This field records the frames a model can be given. 11 take a first and a last frame, 3 take several keyframes, 7 a first frame only; 2 are silent and 1 could not be read.
A last frame pins where a shot ends, which is what lets it hand over cleanly to the next one.
2Readings and how many models carry each
- First and last frame: 11 models
- Several keyframes: 3 models
- First frame only: 7 models
- N/A, docs unreadable: 1 model
- None in the docs: 2 models
3Single models on this field
- Adobe Firefly — First and last frame
- Google Veo — First and last frame
- Grok Imagine — First frame only
- HunyuanVideo 1.5 — First frame only
- Kling AI — First and last frame
- Leonardo Motion 2.0 — First frame only
- LTX — Several keyframes
- LTX Studio — First frame only
- Luma Dream Machine — First and last frame
- Midjourney — First and last frame
- MiniMax Hailuo — First and last frame
- Moonvalley Marey — Several keyframes
- Open-Sora 2.0 — First frame only
- Pika — First and last frame
- PixVerse — First and last frame
- Runway — Several keyframes
- SkyReels — First and last frame
- Sora — First frame only
- Step-Video-TI2V — First frame only
- Vidu — First and last frame
- Wan — First and last frame
4The other five fields
How a camera move is asked for · Shot sizes and angles in the docs · Cuts inside one generation · A negative prompt · A setting for how much the picture moves