# inference.minimax.h3.chili.img2vid.v0

Source: https://docs.prodia.com/job-types/inference-minimax-h3-chili-img2vid-v0/

The `inference.minimax.h3.chili.img2vid.v0` job animates an uploaded image
into a 24 fps video with synchronized stereo audio.

Upload the starting image as a job input and set `first_frame` to its
filename. You can also upload an ending image and name it in `last_frame`
to guide the closing frame. If these fields are omitted, the first upload
is the starting frame and the second upload, when present, is the ending
frame.

```json
{
    "type": "inference.minimax.h3.chili.img2vid.v0",
    "config": {
        "prompt": "the scene comes to life, camera slowly pushing in",
        "first_frame": "input.jpg",
        "duration": 8
    }
}
```

## Prompting

The prompt is used exactly as written: nothing rewrites or expands it before
it reaches the model, which was trained on descriptive captions. Describe
the shot rather than making a request: the subject, setting, time of day,
weather, lighting, camera move and motion. For example, "show me what
christmas would be like in Tokyo" tends to produce a generic winter scene,
while "Shibuya crossing in Tokyo on Christmas Eve at night, light snow
falling, crowds with umbrellas, a giant illuminated Christmas tree, neon
signs reflecting in the wet street, slow cinematic dolly shot" produces the
intended scene. The input image already fixes the subject and composition,
so use the prompt to describe the motion and change you want from it. This
job type runs a distilled 8-evaluation recipe, so it follows the prompt less
closely than full-step generation; vague prompts steer it even less, so a
detailed description matters more here.

## Structured prompt format

MiniMax trains H3 on a structured prompt, not on free text. Sending that
structure yourself is the most reliable way to control the soundtrack: on a
24-prompt bank rendered on this tier, 10 of 24 free-text prompts came back
with an unrequested music bed, and 0 of 24 did when the same prompts were
sent in this format (same seeds, same duration). The format adds three
things free text usually leaves to the model's own judgement: an explicit
soundscape, an explicit music decision, and an explicit statement of whether
anyone speaks.

Rules that apply to every section below:

- A line is spoken only when it is written as dialogue:
  `she (S1) says softly: <d>[English] Don't tell me you forgot again.</d>`.
  `(S1)` numbers the speaker, `<d>…</d>` encloses the spoken words, and the
  language tag is always `[English]` (the model voices other languages inside
  the tag as written). Put dialogue last in the shot: prose after a spoken
  line tends to be voiced too.
- When nobody speaks, say so: `She does not speak.`, `He does not speak.`
  or, for a scene with no single subject, `No spoken dialogue.` Without this
  sentence the model may invent speech.
- `overall_soundscape:` is one sentence of diegetic sound, i.e. what the
  scene itself produces. For a person: `Soft room tone, her quiet breathing
  and the faint rustle of fabric as she moves.` For a scene: `Natural ambient
  sound matching the scene and its visible actions.`
- `non_diegetic_music:` is `N/A` unless you want a score, in which case
  describe it in one sentence, e.g. `Calm ambient piano plays throughout.`
- Separate sections with a blank line. The whole prompt, format included,
  must stay within the 7000-character limit.
- Write the visual description exactly as the Prompting section above
  recommends; the format wraps it, it does not replace it.

Beyond the soundtrack, the same format carries the rest of what the model
was trained to read:

- Write the description as a timeline, not a caption: what is visible and
  audible first, then the actions, reactions and state changes in the order
  they happen. Every detail should be something that can be seen or heard;
  requests like "make it cinematic" steer little.
- Give camera movement as type, amplitude and speed: "the camera pushes in
  with small amplitude at slow speed", "trucks right slowly", "holds a
  locked-off shot".
- For more than one shot, keep `[Shot 1]` without a timestamp and start each
  later shot with a strictly increasing cut time inside the duration:
  `[Shot 2] At 00:05.000, the camera cuts to a close-up of steam rising from
  the sliced bread.`
- Keep a speaker's id across shots. For narration that is not spoken on
  screen, use the exact phrase "says in an off-screen voiceover" and add
  that the on-screen character's lips remain closed. When a line crosses a
  cut, mark both parts with `<scenetrans>` and say the audio continues
  across the cut; when the clip ends mid-sentence, mark the line with
  `<cutoff>`.
- When you do want a score, describe it as instrumentation, tempo and
  dynamics ("sparse piano at a slow tempo, joined by low strings that build
  and fade") rather than mood words.
- Text that must appear on screen is spelled out verbatim in the prompt.
- An unspecified clip gets natural ambience; write `overall_soundscape: N/A`
  only when you want silence.

Image-to-video adds one line before the three sections that binds the
uploaded first frame to the shot as `<Picture 1>`, and the shot opens by
saying the frame's appearance, setting and framing are kept. Describe the
motion and change you want from the frame; the picture already fixes the
subject.

```
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.

integrated_multimodal_description: [Shot 1] The subject shown in <Picture 1> is the first frame; its appearance, setting and framing are kept. She hugs her knees tighter, turns her head toward the lens and lets a slow, warm smile spread. She does not speak.

overall_soundscape: Soft room tone, her quiet breathing and the faint rustle of fabric as she moves.

non_diegetic_music: N/A
```

When `last_frame` is also uploaded, it is `<Picture 2>`; mention it the same
way if the ending should match it.

`prompt` is required and must contain 3–7000 characters. Describe both the
visual scene and the sounds you want to hear.

`duration` accepts whole seconds from 4 to 15 and defaults to 6. The actual
video may be slightly longer than requested: 4 seconds produces about
4.46 seconds, and 15 seconds produces about 15.08 seconds.

`resolution` supports only `768P`, which is also the default. Exact output
dimensions depend on the aspect ratio. `seed` accepts an integer from 0 to
2147483647 for reproducible generation; omit it to use a random seed.

The output aspect ratio follows the starting image. `aspect_ratio` accepts
only `adaptive`, which is also the default.

## Schema

```json
{
	"type": "object",
	"required": [
		"type",
		"config"
	],
	"additionalProperties": false,
	"properties": {
		"type": {
			"type": "string",
			"enum": [
				"inference.minimax.h3.base.img2vid.v0",
				"inference.minimax.h3.fast.img2vid.v0",
				"inference.minimax.h3.base.img2vid.v1",
				"inference.minimax.h3.fast.img2vid.v1",
				"inference.minimax.h3.turbo.img2vid.v0",
				"inference.minimax.h3.hyper.img2vid.v0",
				"inference.minimax.h3.chili.img2vid.v0"
			]
		},
		"config": {
			"type": "object",
			"required": [
				"prompt"
			],
			"additionalProperties": false,
			"properties": {
				"first_frame": {
					"type": "string",
					"format": "filename",
					"example": "first_frame.png",
					"description": "Set the starting frame for the video. Optional: defaults to the first uploaded input."
				},
				"last_frame": {
					"type": "string",
					"format": "filename",
					"example": "last_frame.png",
					"description": "Set the ending frame for the video. Optional: defaults to the second uploaded input, when present."
				},
				"prompt": {
					"type": "string",
					"minLength": 3,
					"maxLength": 7000,
					"default": "a dancing cat under moonlight",
					"description": "Description of the desired video and audio."
				},
				"duration": {
					"type": "integer",
					"minimum": 4,
					"maximum": 15,
					"default": 6,
					"description": "Duration of the video in seconds. Rounded up to the model's frame grid (4 s returns 4.46 s, 15 s returns 15.08 s)."
				},
				"aspect_ratio": {
					"type": "string",
					"enum": [
						"adaptive"
					],
					"default": "adaptive",
					"description": "The aspect ratio always derives from the input image, so only \"adaptive\" is accepted."
				},
				"resolution": {
					"type": "string",
					"enum": [
						"768P"
					],
					"default": "768P",
					"description": "Only 768P is supported: the canvas targets a 768px short edge with a 768x1344 pixel area cap and 32px rounding; exact width and height follow the aspect ratio of the input image."
				},
				"seed": {
					"type": "integer",
					"minimum": 0,
					"maximum": 2147483647,
					"description": "Seed for reproducible generation. Random when omitted."
				}
			}
		}
	}
}
```
