fal-endpoint-types 1.3.51 → 1.3.53
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +8 -4
- package/types/fal/endpoints/components.d.ts +2423 -454
- package/types/fal/endpoints/index.d.ts +2171 -1216
- package/types/fal/endpoints/schema.d.ts +76995 -63847
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
export interface
|
|
1
|
+
export interface WhisperChunk {
|
|
2
2
|
/**
|
|
3
3
|
* Text
|
|
4
4
|
* @description Transcription of the chunk
|
|
@@ -11,22 +11,137 @@ export interface WhisperChunk_1 {
|
|
|
11
11
|
timestamp: [number, number];
|
|
12
12
|
}
|
|
13
13
|
|
|
14
|
-
export interface
|
|
14
|
+
export interface WeightInput {
|
|
15
15
|
/**
|
|
16
|
-
*
|
|
17
|
-
* @
|
|
16
|
+
* Label
|
|
17
|
+
* @default Weight
|
|
18
|
+
* @enum {string}
|
|
18
19
|
*/
|
|
19
|
-
|
|
20
|
+
label?: 'Weight' | 'Net Weight';
|
|
20
21
|
/**
|
|
21
|
-
*
|
|
22
|
-
* @
|
|
22
|
+
* Unit
|
|
23
|
+
* @enum {string}
|
|
23
24
|
*/
|
|
24
|
-
|
|
25
|
+
unit: 'lb' | 'oz' | 'g' | 'kg';
|
|
26
|
+
value: number;
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
export interface WebSearchUserLocation {
|
|
25
30
|
/**
|
|
26
|
-
*
|
|
27
|
-
* @description
|
|
31
|
+
* City
|
|
32
|
+
* @description City name, e.g. 'San Francisco'.
|
|
28
33
|
*/
|
|
29
|
-
|
|
34
|
+
city?: string;
|
|
35
|
+
/**
|
|
36
|
+
* Country
|
|
37
|
+
* @description Two-letter country code, e.g. 'US'.
|
|
38
|
+
*/
|
|
39
|
+
country?: string;
|
|
40
|
+
/**
|
|
41
|
+
* Region
|
|
42
|
+
* @description Region or state, e.g. 'California'.
|
|
43
|
+
*/
|
|
44
|
+
region?: string;
|
|
45
|
+
/**
|
|
46
|
+
* Timezone
|
|
47
|
+
* @description IANA timezone, e.g. 'America/Los_Angeles'.
|
|
48
|
+
*/
|
|
49
|
+
timezone?: string;
|
|
50
|
+
/**
|
|
51
|
+
* Type
|
|
52
|
+
* @description Location type. Only 'approximate' is supported.
|
|
53
|
+
* @default approximate
|
|
54
|
+
* @constant
|
|
55
|
+
*/
|
|
56
|
+
type?: 'approximate';
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
export interface WebSearchOptions {
|
|
60
|
+
/**
|
|
61
|
+
* Allowed Domains
|
|
62
|
+
* @description Limit results to these domains. Supported by Exa and most native providers (not Google native search).
|
|
63
|
+
*/
|
|
64
|
+
allowed_domains?: string[];
|
|
65
|
+
/**
|
|
66
|
+
* Engine
|
|
67
|
+
* @description Search engine to use. 'auto' uses native provider search when available and falls back to Exa. 'native' prefers the provider's built-in web search (OpenAI, Anthropic, Google, xAI, Perplexity), falling back to Exa for models without native support. 'exa' always uses Exa's search API.
|
|
68
|
+
* @default auto
|
|
69
|
+
* @enum {string}
|
|
70
|
+
*/
|
|
71
|
+
engine?: 'auto' | 'native' | 'exa';
|
|
72
|
+
/**
|
|
73
|
+
* Excluded Domains
|
|
74
|
+
* @description Exclude results from these domains. Supported by Exa and some native providers (not OpenAI or Google native search).
|
|
75
|
+
*/
|
|
76
|
+
excluded_domains?: string[];
|
|
77
|
+
/**
|
|
78
|
+
* Max Characters
|
|
79
|
+
* @description Exact maximum characters of content per result (1-100,000). Applies to the Exa engine; ignored with native provider search. Takes precedence over search_context_size when both are set.
|
|
80
|
+
*/
|
|
81
|
+
max_characters?: number;
|
|
82
|
+
/**
|
|
83
|
+
* Max Results
|
|
84
|
+
* @description Maximum results per search call (1-25). Applies to the Exa engine; ignored with native provider search. Defaults to 5.
|
|
85
|
+
*/
|
|
86
|
+
max_results?: number;
|
|
87
|
+
/**
|
|
88
|
+
* Max Total Results
|
|
89
|
+
* @description Maximum total results across all search calls in a single request. Useful for controlling cost and context size in agentic loops.
|
|
90
|
+
*/
|
|
91
|
+
max_total_results?: number;
|
|
92
|
+
/**
|
|
93
|
+
* Max Uses
|
|
94
|
+
* @description Maximum number of searches the model may perform in a single request. Once reached, further search calls return an error result instead of executing. With native provider search, forwarded only to Anthropic; other native providers ignore it.
|
|
95
|
+
*/
|
|
96
|
+
max_uses?: number;
|
|
97
|
+
/**
|
|
98
|
+
* Search Context Size
|
|
99
|
+
* @description How much content to retrieve per result. For Exa: low=5K, medium=15K, high=30K characters per result; when omitted, Exa picks adaptively (~2-4K per result). Ignored with native provider search. Overridden by max_characters when both are set.
|
|
100
|
+
*/
|
|
101
|
+
search_context_size?: 'low' | 'medium' | 'high';
|
|
102
|
+
user_location?: WebSearchUserLocation;
|
|
103
|
+
}
|
|
104
|
+
|
|
105
|
+
export interface Watermark {
|
|
106
|
+
/**
|
|
107
|
+
* Image Url
|
|
108
|
+
* @description Logo/watermark image URL. If empty, no watermark is added.
|
|
109
|
+
*/
|
|
110
|
+
image_url?: string;
|
|
111
|
+
/**
|
|
112
|
+
* Margin
|
|
113
|
+
* @description Inset from the edge. '%' (0–49%) of the canvas, or 'px'.
|
|
114
|
+
* @default 3%
|
|
115
|
+
* @example 3%
|
|
116
|
+
*/
|
|
117
|
+
margin?: string;
|
|
118
|
+
/**
|
|
119
|
+
* Opacity
|
|
120
|
+
* @description Watermark opacity (0–1).
|
|
121
|
+
* @default 1
|
|
122
|
+
*/
|
|
123
|
+
opacity?: number;
|
|
124
|
+
/**
|
|
125
|
+
* Position
|
|
126
|
+
* @description Where to place the watermark.
|
|
127
|
+
* @default bottom_right
|
|
128
|
+
* @example bottom_right
|
|
129
|
+
* @enum {string}
|
|
130
|
+
*/
|
|
131
|
+
position?: 'top_left' | 'top_right' | 'bottom_left' | 'bottom_right' | 'center';
|
|
132
|
+
/**
|
|
133
|
+
* Remove Background
|
|
134
|
+
* @description Remove the watermark image's own background (via background removal) before overlaying it.
|
|
135
|
+
* @default false
|
|
136
|
+
*/
|
|
137
|
+
remove_background?: boolean;
|
|
138
|
+
/**
|
|
139
|
+
* Scale
|
|
140
|
+
* @description Watermark width as a fraction of the canvas width.
|
|
141
|
+
* @default 0.1
|
|
142
|
+
* @example 0.1
|
|
143
|
+
*/
|
|
144
|
+
scale?: number;
|
|
30
145
|
}
|
|
31
146
|
|
|
32
147
|
export interface VoiceSetting {
|
|
@@ -105,6 +220,135 @@ export interface VoiceModify {
|
|
|
105
220
|
timbre?: number;
|
|
106
221
|
}
|
|
107
222
|
|
|
223
|
+
export interface Voice {
|
|
224
|
+
/**
|
|
225
|
+
* Name
|
|
226
|
+
* @description Predefined voice, chosen by name. Ignored when `id` is set.
|
|
227
|
+
* @default Jennie
|
|
228
|
+
* @enum {string}
|
|
229
|
+
*/
|
|
230
|
+
name?:
|
|
231
|
+
| 'Jennie'
|
|
232
|
+
| 'Stella'
|
|
233
|
+
| 'Max'
|
|
234
|
+
| 'Hayes'
|
|
235
|
+
| 'Elara'
|
|
236
|
+
| 'Cleo'
|
|
237
|
+
| 'Fisher'
|
|
238
|
+
| 'Corin'
|
|
239
|
+
| 'Thaddeus'
|
|
240
|
+
| 'Lucina'
|
|
241
|
+
| 'Acadia'
|
|
242
|
+
| 'Huxley'
|
|
243
|
+
| 'Winslet'
|
|
244
|
+
| 'Jethro'
|
|
245
|
+
| 'Elio'
|
|
246
|
+
| 'Rupert'
|
|
247
|
+
| 'Eira'
|
|
248
|
+
| 'Nyra'
|
|
249
|
+
| 'Arian'
|
|
250
|
+
| 'Lily'
|
|
251
|
+
| 'Pierce'
|
|
252
|
+
| 'Kaela'
|
|
253
|
+
| 'Elowen'
|
|
254
|
+
| 'Freya'
|
|
255
|
+
| 'Lenny'
|
|
256
|
+
| 'Alessa'
|
|
257
|
+
| 'Pandora'
|
|
258
|
+
| 'Fia'
|
|
259
|
+
| 'Abbott'
|
|
260
|
+
| 'Kael'
|
|
261
|
+
| 'Orla'
|
|
262
|
+
| 'Sable'
|
|
263
|
+
| 'Marnie'
|
|
264
|
+
| 'Sera'
|
|
265
|
+
| 'Virel'
|
|
266
|
+
| 'Liora'
|
|
267
|
+
| 'Riven'
|
|
268
|
+
| 'Elys'
|
|
269
|
+
| 'Dreena'
|
|
270
|
+
| 'Rhea'
|
|
271
|
+
| 'Vela'
|
|
272
|
+
| 'Nymera'
|
|
273
|
+
| 'Isolde'
|
|
274
|
+
| 'Lirien'
|
|
275
|
+
| 'Zella'
|
|
276
|
+
| 'Avenna'
|
|
277
|
+
| 'Mirelle'
|
|
278
|
+
| 'Calia'
|
|
279
|
+
| 'Lunea'
|
|
280
|
+
| 'Lucan'
|
|
281
|
+
| 'Tarian'
|
|
282
|
+
| 'Arlo'
|
|
283
|
+
| 'Jovan'
|
|
284
|
+
| 'Neron'
|
|
285
|
+
| 'Ziven'
|
|
286
|
+
| 'Dax'
|
|
287
|
+
| 'Orien'
|
|
288
|
+
| 'Lior'
|
|
289
|
+
| 'Eryx'
|
|
290
|
+
| 'Tyren'
|
|
291
|
+
| 'Nox'
|
|
292
|
+
| 'Elric'
|
|
293
|
+
| 'Varian'
|
|
294
|
+
| 'Zoran'
|
|
295
|
+
| 'Miro'
|
|
296
|
+
| 'Dalen'
|
|
297
|
+
| 'Ronix'
|
|
298
|
+
| 'Jarek'
|
|
299
|
+
| 'Nyxie'
|
|
300
|
+
| 'Soren'
|
|
301
|
+
| 'Viona'
|
|
302
|
+
| 'Selene'
|
|
303
|
+
| 'Rachiel'
|
|
304
|
+
| 'Corbin'
|
|
305
|
+
| 'Abigail'
|
|
306
|
+
| 'Faith'
|
|
307
|
+
| 'Kimberly'
|
|
308
|
+
| 'Dave'
|
|
309
|
+
| 'Grace'
|
|
310
|
+
| 'Alden'
|
|
311
|
+
| 'Renly'
|
|
312
|
+
| 'Violet'
|
|
313
|
+
| 'Joel'
|
|
314
|
+
| 'Xavier'
|
|
315
|
+
| 'Esmeralda'
|
|
316
|
+
| 'Robert'
|
|
317
|
+
| 'Lila'
|
|
318
|
+
| 'Brooks'
|
|
319
|
+
| 'Lennox'
|
|
320
|
+
| 'Vanessa'
|
|
321
|
+
| 'Simon'
|
|
322
|
+
| 'Nyomi'
|
|
323
|
+
| 'Jack'
|
|
324
|
+
| 'Penelope'
|
|
325
|
+
| 'Brayden'
|
|
326
|
+
| 'Abel'
|
|
327
|
+
| 'Nellie'
|
|
328
|
+
| 'Connie'
|
|
329
|
+
| 'Andrew'
|
|
330
|
+
| 'Lincoln';
|
|
331
|
+
}
|
|
332
|
+
|
|
333
|
+
export interface VocabularyEntry {
|
|
334
|
+
/**
|
|
335
|
+
* Replaces
|
|
336
|
+
* @description Misspellings that should be replaced with `word`. Matched whole-word and case-insensitively — list each misspelling once; you don't need to enumerate casings (e.g. `['vid']` already covers `Vid`, `VID`).
|
|
337
|
+
* @example [
|
|
338
|
+
* "vid",
|
|
339
|
+
* "feed"
|
|
340
|
+
* ]
|
|
341
|
+
*/
|
|
342
|
+
replaces: string[];
|
|
343
|
+
/**
|
|
344
|
+
* Word
|
|
345
|
+
* @description The correctly-spelled term. Brand names, product names, and domain jargon work best.
|
|
346
|
+
* @example VEED
|
|
347
|
+
* @example TikTok
|
|
348
|
+
*/
|
|
349
|
+
word: string;
|
|
350
|
+
}
|
|
351
|
+
|
|
108
352
|
export interface VideoFormat {
|
|
109
353
|
/**
|
|
110
354
|
* Bitrate
|
|
@@ -267,26 +511,6 @@ export interface VideoConditioningInput {
|
|
|
267
511
|
video_url: string;
|
|
268
512
|
}
|
|
269
513
|
|
|
270
|
-
export interface VideoCondition {
|
|
271
|
-
/**
|
|
272
|
-
* Start Frame Number
|
|
273
|
-
* @description The frame number to start the condition on.
|
|
274
|
-
* @default 0
|
|
275
|
-
*/
|
|
276
|
-
start_frame_number?: number;
|
|
277
|
-
/**
|
|
278
|
-
* Strength
|
|
279
|
-
* @description The strength of the condition.
|
|
280
|
-
* @default 1
|
|
281
|
-
*/
|
|
282
|
-
strength?: number;
|
|
283
|
-
/**
|
|
284
|
-
* Video Url
|
|
285
|
-
* @description The URL of the video to use as input.
|
|
286
|
-
*/
|
|
287
|
-
video_url: string;
|
|
288
|
-
}
|
|
289
|
-
|
|
290
514
|
export interface VideoAgentConfig {
|
|
291
515
|
/**
|
|
292
516
|
* Avatar
|
|
@@ -1732,6 +1956,54 @@ export interface VibeVoiceSpeaker {
|
|
|
1732
1956
|
| 'Xinran [ZH]';
|
|
1733
1957
|
}
|
|
1734
1958
|
|
|
1959
|
+
export interface Vgl {
|
|
1960
|
+
aesthetics?: Aesthetics_1;
|
|
1961
|
+
/**
|
|
1962
|
+
* Artistic Style
|
|
1963
|
+
* @description The artistic style of the image to be generated.
|
|
1964
|
+
*/
|
|
1965
|
+
artistic_style?: string;
|
|
1966
|
+
/**
|
|
1967
|
+
* Background Setting
|
|
1968
|
+
* @description The background setting of the image to be generated.
|
|
1969
|
+
*/
|
|
1970
|
+
background_setting?: string;
|
|
1971
|
+
/**
|
|
1972
|
+
* Context
|
|
1973
|
+
* @description The context of the image to be generated.
|
|
1974
|
+
*/
|
|
1975
|
+
context?: string;
|
|
1976
|
+
/**
|
|
1977
|
+
* Edit Instruction
|
|
1978
|
+
* @description The edit instruction for the image.
|
|
1979
|
+
*/
|
|
1980
|
+
edit_instruction?: string;
|
|
1981
|
+
lighting?: Lighting_1;
|
|
1982
|
+
/**
|
|
1983
|
+
* Objects
|
|
1984
|
+
* @description A list of objects in the image to be generated, along with their attributes and relationships to other objects in the image.
|
|
1985
|
+
* @default []
|
|
1986
|
+
*/
|
|
1987
|
+
objects?: PromptObject_1[];
|
|
1988
|
+
photographic_characteristics?: PhotographicCharacteristics_1;
|
|
1989
|
+
/**
|
|
1990
|
+
* Short Description
|
|
1991
|
+
* @description A short description of the image to be generated.
|
|
1992
|
+
*/
|
|
1993
|
+
short_description?: string;
|
|
1994
|
+
/**
|
|
1995
|
+
* Style Medium
|
|
1996
|
+
* @description The style medium of the image to be generated.
|
|
1997
|
+
*/
|
|
1998
|
+
style_medium?: string;
|
|
1999
|
+
/**
|
|
2000
|
+
* Text Render
|
|
2001
|
+
* @description A list of text to be rendered in the image.
|
|
2002
|
+
* @default []
|
|
2003
|
+
*/
|
|
2004
|
+
text_render?: { [x: string]: any }[];
|
|
2005
|
+
}
|
|
2006
|
+
|
|
1735
2007
|
export interface Validation {
|
|
1736
2008
|
/**
|
|
1737
2009
|
* Image Url
|
|
@@ -1758,7 +2030,43 @@ export interface V2VValidation {
|
|
|
1758
2030
|
reference_video_url: string;
|
|
1759
2031
|
}
|
|
1760
2032
|
|
|
1761
|
-
export interface
|
|
2033
|
+
export interface V2VMaskedValidation {
|
|
2034
|
+
/**
|
|
2035
|
+
* Mask Url
|
|
2036
|
+
* @description URL to the mask (image or video). Standard convention: WHITE marks the region to regenerate/edit, BLACK is kept unchanged.
|
|
2037
|
+
*/
|
|
2038
|
+
mask_url: string;
|
|
2039
|
+
/**
|
|
2040
|
+
* Prompt
|
|
2041
|
+
* @description The prompt to use for validation.
|
|
2042
|
+
*/
|
|
2043
|
+
prompt: string;
|
|
2044
|
+
/**
|
|
2045
|
+
* Reference Video Url
|
|
2046
|
+
* @description URL to the reference (control) video that guides the regenerated region.
|
|
2047
|
+
*/
|
|
2048
|
+
reference_video_url: string;
|
|
2049
|
+
/**
|
|
2050
|
+
* Video Url
|
|
2051
|
+
* @description URL to the source video. Its UNMASKED region is kept pixel-faithful and the masked region is regenerated.
|
|
2052
|
+
*/
|
|
2053
|
+
video_url: string;
|
|
2054
|
+
}
|
|
2055
|
+
|
|
2056
|
+
export interface V2AValidation {
|
|
2057
|
+
/**
|
|
2058
|
+
* Prompt
|
|
2059
|
+
* @description The prompt to use for validation.
|
|
2060
|
+
*/
|
|
2061
|
+
prompt: string;
|
|
2062
|
+
/**
|
|
2063
|
+
* Video Url
|
|
2064
|
+
* @description URL to the silent video the model should generate audio for.
|
|
2065
|
+
*/
|
|
2066
|
+
video_url: string;
|
|
2067
|
+
}
|
|
2068
|
+
|
|
2069
|
+
export interface UsageInfo_2 {
|
|
1762
2070
|
/**
|
|
1763
2071
|
* Decode Time Ms
|
|
1764
2072
|
* @description Time taken for decoding in milliseconds
|
|
@@ -1786,7 +2094,7 @@ export interface UsageInfo_1 {
|
|
|
1786
2094
|
ttft_ms: number;
|
|
1787
2095
|
}
|
|
1788
2096
|
|
|
1789
|
-
export interface
|
|
2097
|
+
export interface UsageInfo_1 {
|
|
1790
2098
|
completion_tokens?: number;
|
|
1791
2099
|
cost: number;
|
|
1792
2100
|
prompt_tokens?: number;
|
|
@@ -1798,6 +2106,19 @@ export interface UsageInfo {
|
|
|
1798
2106
|
total_tokens?: number;
|
|
1799
2107
|
}
|
|
1800
2108
|
|
|
2109
|
+
export interface UsageInfo {
|
|
2110
|
+
/**
|
|
2111
|
+
* Input Tokens
|
|
2112
|
+
* @description Number of input tokens processed.
|
|
2113
|
+
*/
|
|
2114
|
+
input_tokens: number;
|
|
2115
|
+
/**
|
|
2116
|
+
* Output Tokens
|
|
2117
|
+
* @description Number of output tokens generated.
|
|
2118
|
+
*/
|
|
2119
|
+
output_tokens: number;
|
|
2120
|
+
}
|
|
2121
|
+
|
|
1801
2122
|
export interface Turn {
|
|
1802
2123
|
speaker_id: number;
|
|
1803
2124
|
text: string;
|
|
@@ -1885,21 +2206,6 @@ export interface TrajectoryParameters {
|
|
|
1885
2206
|
theta: number[];
|
|
1886
2207
|
}
|
|
1887
2208
|
|
|
1888
|
-
export interface Trajectory {
|
|
1889
|
-
/**
|
|
1890
|
-
* X
|
|
1891
|
-
* @description X coordinate of the motion trajectory
|
|
1892
|
-
* @example 279
|
|
1893
|
-
*/
|
|
1894
|
-
x: number;
|
|
1895
|
-
/**
|
|
1896
|
-
* Y
|
|
1897
|
-
* @description Y coordinate of the motion trajectory
|
|
1898
|
-
* @example 219
|
|
1899
|
-
*/
|
|
1900
|
-
y: number;
|
|
1901
|
-
}
|
|
1902
|
-
|
|
1903
2209
|
export interface Track {
|
|
1904
2210
|
/**
|
|
1905
2211
|
* Id
|
|
@@ -1910,7 +2216,7 @@ export interface Track {
|
|
|
1910
2216
|
* Keyframes
|
|
1911
2217
|
* @description List of keyframes that make up this track
|
|
1912
2218
|
*/
|
|
1913
|
-
keyframes:
|
|
2219
|
+
keyframes: Keyframe_1[];
|
|
1914
2220
|
/**
|
|
1915
2221
|
* Type
|
|
1916
2222
|
* @description Type of track ('video', 'audio', or 'image')
|
|
@@ -2108,8 +2414,42 @@ export interface TextRender {
|
|
|
2108
2414
|
text: string;
|
|
2109
2415
|
}
|
|
2110
2416
|
|
|
2111
|
-
export interface
|
|
2417
|
+
export interface TextCustomizations {
|
|
2418
|
+
/**
|
|
2419
|
+
* Baseline (all words)
|
|
2420
|
+
* @description Baseline styling applied to every word in the transcript. This is what a reader sees by default, before any per-word emphasis is applied.
|
|
2421
|
+
*/
|
|
2422
|
+
baseline?: TextCustomization;
|
|
2423
|
+
/**
|
|
2424
|
+
* Highlighted (mid-rank)
|
|
2425
|
+
* @description Mid-rank words (automatically marked as noteworthy: key nouns, action verbs, salient adjectives). Presets typically bump size or weight on these.
|
|
2426
|
+
*/
|
|
2427
|
+
highlighted?: TextCustomization;
|
|
2428
|
+
}
|
|
2429
|
+
|
|
2430
|
+
export interface TextCustomization {
|
|
2431
|
+
/**
|
|
2432
|
+
* Color
|
|
2433
|
+
* @description Override the text color for this tier.
|
|
2434
|
+
*/
|
|
2435
|
+
color?: string;
|
|
2436
|
+
/**
|
|
2437
|
+
* Font
|
|
2438
|
+
* @description Override the font used for this text tier. Must be a supported Google Font — see https://www.veed.io/api/v1/subtitle-renders/fonts for the canonical list. Unrecognized fonts are rejected with a 400.
|
|
2439
|
+
*/
|
|
2440
|
+
font?: string;
|
|
2441
|
+
/**
|
|
2442
|
+
* Weight
|
|
2443
|
+
* @description Font weight 100-900. Values >= 700 render as bold
|
|
2444
|
+
*/
|
|
2445
|
+
weight?: number;
|
|
2446
|
+
}
|
|
2447
|
+
|
|
2448
|
+
export interface TailoredStructuredPrompt {
|
|
2449
|
+
action_description?: string;
|
|
2450
|
+
actor_prefix?: string;
|
|
2112
2451
|
aesthetics?: Aesthetics_1;
|
|
2452
|
+
art_direction?: string;
|
|
2113
2453
|
/**
|
|
2114
2454
|
* Artistic Style
|
|
2115
2455
|
* @description The artistic style of the image to be generated.
|
|
@@ -2120,11 +2460,6 @@ export interface StructuredPrompt_2 {
|
|
|
2120
2460
|
* @description The background setting of the image to be generated.
|
|
2121
2461
|
*/
|
|
2122
2462
|
background_setting?: string;
|
|
2123
|
-
/**
|
|
2124
|
-
* Color Palette
|
|
2125
|
-
* @description A list of colors that define the overall color palette of the image.
|
|
2126
|
-
*/
|
|
2127
|
-
color_palette?: Color[];
|
|
2128
2463
|
/**
|
|
2129
2464
|
* Context
|
|
2130
2465
|
* @description The context of the image to be generated.
|
|
@@ -2148,61 +2483,154 @@ export interface StructuredPrompt_2 {
|
|
|
2148
2483
|
* @description The style medium of the image to be generated.
|
|
2149
2484
|
*/
|
|
2150
2485
|
style_medium?: string;
|
|
2486
|
+
sub_trigger_word?: string;
|
|
2151
2487
|
/**
|
|
2152
2488
|
* Text Render
|
|
2153
2489
|
* @description A list of text to be rendered in the image.
|
|
2154
2490
|
* @default []
|
|
2155
2491
|
*/
|
|
2156
2492
|
text_render?: { [x: string]: any }[];
|
|
2493
|
+
trigger_word?: string;
|
|
2157
2494
|
}
|
|
2158
2495
|
|
|
2159
|
-
export interface
|
|
2160
|
-
aesthetics: AestheticsDetails;
|
|
2496
|
+
export interface T2AValidation {
|
|
2161
2497
|
/**
|
|
2162
|
-
*
|
|
2163
|
-
* @description
|
|
2498
|
+
* Prompt
|
|
2499
|
+
* @description The prompt to use for validation.
|
|
2164
2500
|
*/
|
|
2165
|
-
|
|
2501
|
+
prompt: string;
|
|
2502
|
+
}
|
|
2503
|
+
|
|
2504
|
+
export interface Sync3GenerationOptions {
|
|
2505
|
+
active_speaker_detection?: Sync3ActiveSpeakerDetection;
|
|
2166
2506
|
/**
|
|
2167
|
-
*
|
|
2168
|
-
* @description
|
|
2507
|
+
* Model Mode
|
|
2508
|
+
* @description Edit region for the model. This is a Sync.so option primarily used by react-1.
|
|
2169
2509
|
*/
|
|
2170
|
-
|
|
2510
|
+
model_mode?: 'lips' | 'face' | 'head' | 'lipsync' | 'emotion' | 'talking_head';
|
|
2171
2511
|
/**
|
|
2172
|
-
*
|
|
2173
|
-
* @description
|
|
2512
|
+
* Occlusion Detection Enabled
|
|
2513
|
+
* @description Whether to detect occlusion during generation. Sync.so handles this automatically for sync-3, so this option is ignored by sync-3.
|
|
2174
2514
|
*/
|
|
2175
|
-
|
|
2176
|
-
lighting: LightingDetails;
|
|
2515
|
+
occlusion_detection_enabled?: boolean;
|
|
2177
2516
|
/**
|
|
2178
|
-
*
|
|
2179
|
-
* @description
|
|
2517
|
+
* Prompt
|
|
2518
|
+
* @description Emotion prompt for generation. This is a Sync.so option primarily used by react-1.
|
|
2180
2519
|
*/
|
|
2181
|
-
|
|
2182
|
-
photographic_characteristics?: PhotographicCharacteristicsDetails;
|
|
2520
|
+
prompt?: 'happy' | 'sad' | 'angry' | 'disgusted' | 'surprised' | 'neutral';
|
|
2183
2521
|
/**
|
|
2184
|
-
*
|
|
2185
|
-
* @description
|
|
2522
|
+
* Sync Mode
|
|
2523
|
+
* @description Defines how to handle duration mismatches between video and audio inputs. Overrides the top-level sync_mode when provided.
|
|
2186
2524
|
*/
|
|
2187
|
-
|
|
2525
|
+
sync_mode?: 'cut_off' | 'loop' | 'bounce' | 'silence' | 'remap';
|
|
2188
2526
|
/**
|
|
2189
|
-
*
|
|
2190
|
-
* @description
|
|
2527
|
+
* Temperature
|
|
2528
|
+
* @description Controls how expressive lipsync can be; 0 is least expressive, 1 is most expressive. Sync.so handles this natively for sync-3, so this option is ignored by sync-3.
|
|
2191
2529
|
*/
|
|
2192
|
-
|
|
2530
|
+
temperature?: number;
|
|
2531
|
+
}
|
|
2532
|
+
|
|
2533
|
+
export interface Sync3ActiveSpeakerDetection {
|
|
2193
2534
|
/**
|
|
2194
|
-
*
|
|
2195
|
-
* @description
|
|
2535
|
+
* Auto Detect
|
|
2536
|
+
* @description Whether to automatically detect and apply generation to the active speaker.
|
|
2196
2537
|
*/
|
|
2197
|
-
|
|
2538
|
+
auto_detect?: boolean;
|
|
2198
2539
|
/**
|
|
2199
|
-
*
|
|
2200
|
-
* @description
|
|
2540
|
+
* Bounding Boxes
|
|
2541
|
+
* @description Per-frame bounding boxes [x1, y1, x2, y2] for the detected face.
|
|
2201
2542
|
*/
|
|
2202
|
-
|
|
2543
|
+
bounding_boxes?: number[][];
|
|
2544
|
+
/**
|
|
2545
|
+
* Bounding Boxes Url
|
|
2546
|
+
* @description URL to a JSON file containing per-frame bounding boxes.
|
|
2547
|
+
*/
|
|
2548
|
+
bounding_boxes_url?: string;
|
|
2549
|
+
/**
|
|
2550
|
+
* Coordinates
|
|
2551
|
+
* @description Reference point [x, y] on the speaker's face in frame_number.
|
|
2552
|
+
*/
|
|
2553
|
+
coordinates?: number[];
|
|
2554
|
+
/**
|
|
2555
|
+
* Face Image
|
|
2556
|
+
* @description Base64 encoded face image for manual speaker selection.
|
|
2557
|
+
*/
|
|
2558
|
+
face_image?: string;
|
|
2559
|
+
/**
|
|
2560
|
+
* Frame Number
|
|
2561
|
+
* @description Frame index for manual speaker selection coordinates.
|
|
2562
|
+
*/
|
|
2563
|
+
frame_number?: number;
|
|
2564
|
+
/**
|
|
2565
|
+
* Use V2
|
|
2566
|
+
* @description Deprecated Sync.so option for active speaker detection v2.
|
|
2567
|
+
*/
|
|
2568
|
+
use_v2?: boolean;
|
|
2569
|
+
/**
|
|
2570
|
+
* V3
|
|
2571
|
+
* @description Whether to use Sync.so's active speaker detection v3.
|
|
2572
|
+
*/
|
|
2573
|
+
v3?: boolean;
|
|
2203
2574
|
}
|
|
2204
2575
|
|
|
2205
|
-
export interface
|
|
2576
|
+
export interface Style {
|
|
2577
|
+
/**
|
|
2578
|
+
* Id
|
|
2579
|
+
* @description Krea style identifier (a LoRA-based preset style) returned by the Krea styles catalog.
|
|
2580
|
+
*/
|
|
2581
|
+
id: string;
|
|
2582
|
+
/**
|
|
2583
|
+
* Strength
|
|
2584
|
+
* @description How strongly the style influences the generated image. Negative values push away from the style.
|
|
2585
|
+
* @default 1
|
|
2586
|
+
*/
|
|
2587
|
+
strength?: number;
|
|
2588
|
+
}
|
|
2589
|
+
|
|
2590
|
+
export interface StructuredPrompt_2 {
|
|
2591
|
+
aesthetics?: Aesthetics_1;
|
|
2592
|
+
/**
|
|
2593
|
+
* Artistic Style
|
|
2594
|
+
* @description The artistic style of the image to be generated.
|
|
2595
|
+
*/
|
|
2596
|
+
artistic_style?: string;
|
|
2597
|
+
/**
|
|
2598
|
+
* Background Setting
|
|
2599
|
+
* @description The background setting of the image to be generated.
|
|
2600
|
+
*/
|
|
2601
|
+
background_setting?: string;
|
|
2602
|
+
/**
|
|
2603
|
+
* Context
|
|
2604
|
+
* @description The context of the image to be generated.
|
|
2605
|
+
*/
|
|
2606
|
+
context?: string;
|
|
2607
|
+
lighting?: Lighting_1;
|
|
2608
|
+
/**
|
|
2609
|
+
* Objects
|
|
2610
|
+
* @description A list of objects in the image to be generated, along with their attributes and relationships to other objects in the image.
|
|
2611
|
+
* @default []
|
|
2612
|
+
*/
|
|
2613
|
+
objects?: PromptObject_1[];
|
|
2614
|
+
photographic_characteristics?: PhotographicCharacteristics_1;
|
|
2615
|
+
/**
|
|
2616
|
+
* Short Description
|
|
2617
|
+
* @description A short description of the image to be generated.
|
|
2618
|
+
*/
|
|
2619
|
+
short_description?: string;
|
|
2620
|
+
/**
|
|
2621
|
+
* Style Medium
|
|
2622
|
+
* @description The style medium of the image to be generated.
|
|
2623
|
+
*/
|
|
2624
|
+
style_medium?: string;
|
|
2625
|
+
/**
|
|
2626
|
+
* Text Render
|
|
2627
|
+
* @description A list of text to be rendered in the image.
|
|
2628
|
+
* @default []
|
|
2629
|
+
*/
|
|
2630
|
+
text_render?: { [x: string]: any }[];
|
|
2631
|
+
}
|
|
2632
|
+
|
|
2633
|
+
export interface StructuredPrompt_1 {
|
|
2206
2634
|
aesthetics?: Aesthetics_1;
|
|
2207
2635
|
/**
|
|
2208
2636
|
* Artistic Style
|
|
@@ -2214,6 +2642,11 @@ export interface StructuredPrompt {
|
|
|
2214
2642
|
* @description The background setting of the image to be generated.
|
|
2215
2643
|
*/
|
|
2216
2644
|
background_setting?: string;
|
|
2645
|
+
/**
|
|
2646
|
+
* Color Palette
|
|
2647
|
+
* @description A list of colors that define the overall color palette of the image.
|
|
2648
|
+
*/
|
|
2649
|
+
color_palette?: Color[];
|
|
2217
2650
|
/**
|
|
2218
2651
|
* Context
|
|
2219
2652
|
* @description The context of the image to be generated.
|
|
@@ -2245,6 +2678,52 @@ export interface StructuredPrompt {
|
|
|
2245
2678
|
text_render?: { [x: string]: any }[];
|
|
2246
2679
|
}
|
|
2247
2680
|
|
|
2681
|
+
export interface StructuredPrompt {
|
|
2682
|
+
aesthetics: AestheticsDetails;
|
|
2683
|
+
/**
|
|
2684
|
+
* Artistic Style
|
|
2685
|
+
* @description describe specific artistic characteristics, 3 words maximum.
|
|
2686
|
+
*/
|
|
2687
|
+
artistic_style: string;
|
|
2688
|
+
/**
|
|
2689
|
+
* Background Setting
|
|
2690
|
+
* @description Describe the overall environment, setting, or background, including any notable background elements.
|
|
2691
|
+
*/
|
|
2692
|
+
background_setting: string;
|
|
2693
|
+
/**
|
|
2694
|
+
* Context
|
|
2695
|
+
* @description Provide any additional context that helps understand the image better.
|
|
2696
|
+
*/
|
|
2697
|
+
context: string;
|
|
2698
|
+
lighting: LightingDetails;
|
|
2699
|
+
/**
|
|
2700
|
+
* Objects
|
|
2701
|
+
* @description List of prominent foreground/midground objects.
|
|
2702
|
+
*/
|
|
2703
|
+
objects: ObjectDescription[];
|
|
2704
|
+
photographic_characteristics?: PhotographicCharacteristicsDetails;
|
|
2705
|
+
/**
|
|
2706
|
+
* Short Description
|
|
2707
|
+
* @description A concise summary of the image content, 200 words maximum.
|
|
2708
|
+
*/
|
|
2709
|
+
short_description: string;
|
|
2710
|
+
/**
|
|
2711
|
+
* Style Medium
|
|
2712
|
+
* @description Identify the artistic style or medium.
|
|
2713
|
+
*/
|
|
2714
|
+
style_medium?: string;
|
|
2715
|
+
/**
|
|
2716
|
+
* Subject Emotions
|
|
2717
|
+
* @description Explicitly describe any visible emotions or expressions on subjects.
|
|
2718
|
+
*/
|
|
2719
|
+
subject_emotions?: string;
|
|
2720
|
+
/**
|
|
2721
|
+
* Text Render
|
|
2722
|
+
* @description List of text renders in the image.
|
|
2723
|
+
*/
|
|
2724
|
+
text_render?: TextRender[];
|
|
2725
|
+
}
|
|
2726
|
+
|
|
2248
2727
|
export interface StructuredInstruction {
|
|
2249
2728
|
aesthetics?: Aesthetics_1;
|
|
2250
2729
|
/**
|
|
@@ -2291,6 +2770,38 @@ export interface StructuredInstruction {
|
|
|
2291
2770
|
* @default []
|
|
2292
2771
|
*/
|
|
2293
2772
|
text_render?: { [x: string]: any }[];
|
|
2773
|
+
[key: string]: any;
|
|
2774
|
+
}
|
|
2775
|
+
|
|
2776
|
+
export interface SpeechTurn {
|
|
2777
|
+
/**
|
|
2778
|
+
* Speaker ID
|
|
2779
|
+
* @description Alias of a configured speaker.
|
|
2780
|
+
*/
|
|
2781
|
+
speaker_id: string;
|
|
2782
|
+
/**
|
|
2783
|
+
* Style Instructions
|
|
2784
|
+
* @description Optional delivery style for this turn.
|
|
2785
|
+
*/
|
|
2786
|
+
style_instructions?: string;
|
|
2787
|
+
/**
|
|
2788
|
+
* Text
|
|
2789
|
+
* @description Verbatim transcript for this turn.
|
|
2790
|
+
*/
|
|
2791
|
+
text: string;
|
|
2792
|
+
}
|
|
2793
|
+
|
|
2794
|
+
export interface SpeechToTextWord {
|
|
2795
|
+
end?: number;
|
|
2796
|
+
speaker_id?: string;
|
|
2797
|
+
start?: number;
|
|
2798
|
+
text: string;
|
|
2799
|
+
/**
|
|
2800
|
+
* Type
|
|
2801
|
+
* @default word
|
|
2802
|
+
* @enum {string}
|
|
2803
|
+
*/
|
|
2804
|
+
type?: 'word' | 'spacing' | 'audio_event';
|
|
2294
2805
|
}
|
|
2295
2806
|
|
|
2296
2807
|
export interface SpeechTimestamp {
|
|
@@ -2306,6 +2817,50 @@ export interface SpeechTimestamp {
|
|
|
2306
2817
|
start: number;
|
|
2307
2818
|
}
|
|
2308
2819
|
|
|
2820
|
+
export interface SpeakerConfig_1 {
|
|
2821
|
+
/**
|
|
2822
|
+
* Speaker ID
|
|
2823
|
+
* @description Speaker alias used in each turn.
|
|
2824
|
+
*/
|
|
2825
|
+
speaker_id: string;
|
|
2826
|
+
/**
|
|
2827
|
+
* Voice
|
|
2828
|
+
* @description Prebuilt voice for this speaker.
|
|
2829
|
+
* @enum {string}
|
|
2830
|
+
*/
|
|
2831
|
+
voice:
|
|
2832
|
+
| 'Achernar'
|
|
2833
|
+
| 'Achird'
|
|
2834
|
+
| 'Algenib'
|
|
2835
|
+
| 'Algieba'
|
|
2836
|
+
| 'Alnilam'
|
|
2837
|
+
| 'Aoede'
|
|
2838
|
+
| 'Autonoe'
|
|
2839
|
+
| 'Callirrhoe'
|
|
2840
|
+
| 'Charon'
|
|
2841
|
+
| 'Despina'
|
|
2842
|
+
| 'Enceladus'
|
|
2843
|
+
| 'Erinome'
|
|
2844
|
+
| 'Fenrir'
|
|
2845
|
+
| 'Gacrux'
|
|
2846
|
+
| 'Iapetus'
|
|
2847
|
+
| 'Kore'
|
|
2848
|
+
| 'Laomedeia'
|
|
2849
|
+
| 'Leda'
|
|
2850
|
+
| 'Orus'
|
|
2851
|
+
| 'Pulcherrima'
|
|
2852
|
+
| 'Puck'
|
|
2853
|
+
| 'Rasalgethi'
|
|
2854
|
+
| 'Sadachbia'
|
|
2855
|
+
| 'Sadaltager'
|
|
2856
|
+
| 'Schedar'
|
|
2857
|
+
| 'Sulafat'
|
|
2858
|
+
| 'Umbriel'
|
|
2859
|
+
| 'Vindemiatrix'
|
|
2860
|
+
| 'Zephyr'
|
|
2861
|
+
| 'Zubenelgenubi';
|
|
2862
|
+
}
|
|
2863
|
+
|
|
2309
2864
|
export interface SpeakerConfig {
|
|
2310
2865
|
/**
|
|
2311
2866
|
* Speaker Id
|
|
@@ -2359,6 +2914,39 @@ export interface Speaker {
|
|
|
2359
2914
|
speaker_id: number;
|
|
2360
2915
|
}
|
|
2361
2916
|
|
|
2917
|
+
export interface SmartResizeResult {
|
|
2918
|
+
/**
|
|
2919
|
+
* Aspect Ratio
|
|
2920
|
+
* @description The nano-banana-pro aspect ratio that was used internally for this target size.
|
|
2921
|
+
*/
|
|
2922
|
+
aspect_ratio: string;
|
|
2923
|
+
/**
|
|
2924
|
+
* Description
|
|
2925
|
+
* @description The description of the generated images.
|
|
2926
|
+
*/
|
|
2927
|
+
description: string;
|
|
2928
|
+
/**
|
|
2929
|
+
* Height
|
|
2930
|
+
* @description The requested target height in pixels.
|
|
2931
|
+
*/
|
|
2932
|
+
height: number;
|
|
2933
|
+
/**
|
|
2934
|
+
* Images
|
|
2935
|
+
* @description The generated images.
|
|
2936
|
+
*/
|
|
2937
|
+
images: ImageFile[];
|
|
2938
|
+
/**
|
|
2939
|
+
* Resolution
|
|
2940
|
+
* @description The nano-banana-pro resolution tier that was used internally for this target size.
|
|
2941
|
+
*/
|
|
2942
|
+
resolution: string;
|
|
2943
|
+
/**
|
|
2944
|
+
* Width
|
|
2945
|
+
* @description The requested target width in pixels.
|
|
2946
|
+
*/
|
|
2947
|
+
width: number;
|
|
2948
|
+
}
|
|
2949
|
+
|
|
2362
2950
|
export interface SigmasInput {
|
|
2363
2951
|
/**
|
|
2364
2952
|
* Array
|
|
@@ -2377,32 +2965,153 @@ export interface SigmasInput {
|
|
|
2377
2965
|
method?: 'default' | 'array';
|
|
2378
2966
|
}
|
|
2379
2967
|
|
|
2380
|
-
export interface
|
|
2968
|
+
export interface ShadowLightSourcePosition {
|
|
2381
2969
|
/**
|
|
2382
|
-
*
|
|
2383
|
-
* @description
|
|
2384
|
-
* @default 65
|
|
2970
|
+
* X
|
|
2971
|
+
* @description Horizontal light position, normalized to image center (-1 to 1). Leave unset to auto-estimate the light from the image.
|
|
2385
2972
|
*/
|
|
2386
|
-
|
|
2973
|
+
x?: number;
|
|
2974
|
+
/**
|
|
2975
|
+
* Y
|
|
2976
|
+
* @description Vertical light position, normalized to image center (-1 to 1). Leave unset to auto-estimate the light from the image.
|
|
2977
|
+
*/
|
|
2978
|
+
y?: number;
|
|
2979
|
+
/**
|
|
2980
|
+
* Z
|
|
2981
|
+
* @description Height above subject (0 to 2). Leave unset to auto-estimate the light from the image.
|
|
2982
|
+
*/
|
|
2983
|
+
z?: number;
|
|
2984
|
+
}
|
|
2985
|
+
|
|
2986
|
+
export interface ShadowLightSource {
|
|
2987
|
+
position?: ShadowLightSourcePosition;
|
|
2988
|
+
/**
|
|
2989
|
+
* Size
|
|
2990
|
+
* @description Apparent emitter size/softness. Higher = softer penumbra. Leave unset to auto-estimate the light from the image.
|
|
2991
|
+
*/
|
|
2992
|
+
size?: number;
|
|
2993
|
+
}
|
|
2994
|
+
|
|
2995
|
+
export interface Shadow {
|
|
2996
|
+
drop?: DropShadow;
|
|
2997
|
+
generative?: GenerativeShadow;
|
|
2998
|
+
/**
|
|
2999
|
+
* Type
|
|
3000
|
+
* @description Shadow style: 'Generative' (generative AI shadow) or 'Drop' (deterministic drop shadow). Leave unset for no shadow.
|
|
3001
|
+
*/
|
|
3002
|
+
type?: 'Generative' | 'Drop';
|
|
3003
|
+
}
|
|
3004
|
+
|
|
3005
|
+
export interface SfxSegmentMeta {
|
|
3006
|
+
/**
|
|
3007
|
+
* Skip Reason
|
|
3008
|
+
* @description Why the segment was left silent, when it was.
|
|
3009
|
+
*/
|
|
3010
|
+
skip_reason?: string;
|
|
3011
|
+
/**
|
|
3012
|
+
* Skipped
|
|
3013
|
+
* @description Whether this segment was left silent. Always false on sfx-v1.0, which generates every segment.
|
|
3014
|
+
* @default false
|
|
3015
|
+
*/
|
|
3016
|
+
skipped?: boolean;
|
|
3017
|
+
/**
|
|
3018
|
+
* Tags
|
|
3019
|
+
* @description Short display labels for the sounds in this segment; may be empty.
|
|
3020
|
+
*/
|
|
3021
|
+
tags?: string[];
|
|
3022
|
+
}
|
|
3023
|
+
|
|
3024
|
+
export interface SfxSegment {
|
|
3025
|
+
/**
|
|
3026
|
+
* End
|
|
3027
|
+
* @description Segment end time in seconds. Must equal the next segment's start (contiguous; no gaps/overlaps); the last segment's end must be <= the video duration.
|
|
3028
|
+
* @default 0
|
|
3029
|
+
*/
|
|
3030
|
+
end?: number;
|
|
2387
3031
|
/**
|
|
2388
3032
|
* Prompt
|
|
2389
|
-
* @description
|
|
2390
|
-
* @
|
|
3033
|
+
* @description SFX / foley description for this segment.
|
|
3034
|
+
* @default
|
|
2391
3035
|
*/
|
|
2392
|
-
prompt
|
|
3036
|
+
prompt?: string;
|
|
3037
|
+
/**
|
|
3038
|
+
* Start
|
|
3039
|
+
* @description Segment start time in seconds (from video start). The FIRST segment's start must be 0.
|
|
3040
|
+
* @default 0
|
|
3041
|
+
*/
|
|
3042
|
+
start?: number;
|
|
3043
|
+
}
|
|
3044
|
+
|
|
3045
|
+
export interface SfxOutputSegment {
|
|
3046
|
+
/**
|
|
3047
|
+
* End
|
|
3048
|
+
* @description End in seconds on the source video timeline.
|
|
3049
|
+
*/
|
|
3050
|
+
end: number;
|
|
3051
|
+
/**
|
|
3052
|
+
* Index
|
|
3053
|
+
* @description Position of the segment, in source video order.
|
|
3054
|
+
*/
|
|
3055
|
+
index: number;
|
|
3056
|
+
meta: SfxSegmentMeta;
|
|
3057
|
+
/**
|
|
3058
|
+
* Start
|
|
3059
|
+
* @description Start in seconds on the source video timeline.
|
|
3060
|
+
*/
|
|
3061
|
+
start: number;
|
|
3062
|
+
}
|
|
3063
|
+
|
|
3064
|
+
export interface SegmentSamplingSettings {
|
|
3065
|
+
/**
|
|
3066
|
+
* Max Tokens
|
|
3067
|
+
* @description Maximum number of tokens to generate.
|
|
3068
|
+
*/
|
|
3069
|
+
max_tokens?: number;
|
|
3070
|
+
/**
|
|
3071
|
+
* Temperature
|
|
3072
|
+
* @description Sampling temperature to use. Higher values will make the output more random, while lower values will make it more focused and deterministic.
|
|
3073
|
+
* @default 1
|
|
3074
|
+
*/
|
|
3075
|
+
temperature?: number;
|
|
3076
|
+
/**
|
|
3077
|
+
* Top P
|
|
3078
|
+
* @description Nucleus sampling probability mass to use, between 0 and 1.
|
|
3079
|
+
* @default 1
|
|
3080
|
+
*/
|
|
3081
|
+
top_p?: number;
|
|
3082
|
+
}
|
|
3083
|
+
|
|
3084
|
+
export interface SeedDream50ProLayerBoundingBox {
|
|
3085
|
+
/**
|
|
3086
|
+
* Absolute
|
|
3087
|
+
* @description Layer bounds as [left, top, right, bottom] pixel coordinates in the output base image coordinate system.
|
|
3088
|
+
*/
|
|
3089
|
+
absolute: number[];
|
|
3090
|
+
/**
|
|
3091
|
+
* Normalized
|
|
3092
|
+
* @description Layer bounds as [left, top, right, bottom] coordinates normalized to the integer range [0, 1000].
|
|
3093
|
+
*/
|
|
3094
|
+
normalized: number[];
|
|
2393
3095
|
}
|
|
2394
3096
|
|
|
2395
|
-
export interface
|
|
3097
|
+
export interface SeedDream50ProLayer {
|
|
3098
|
+
bounding_box?: SeedDream50ProLayerBoundingBox;
|
|
2396
3099
|
/**
|
|
2397
|
-
*
|
|
2398
|
-
* @description
|
|
3100
|
+
* Description
|
|
3101
|
+
* @description Detailed model-generated description of the layer. Omitted for the base image.
|
|
3102
|
+
*/
|
|
3103
|
+
description?: string;
|
|
3104
|
+
image: Image;
|
|
3105
|
+
/**
|
|
3106
|
+
* Name
|
|
3107
|
+
* @description Model-generated label for the layer. Omitted for the base image.
|
|
2399
3108
|
*/
|
|
2400
|
-
|
|
3109
|
+
name?: string;
|
|
2401
3110
|
/**
|
|
2402
|
-
*
|
|
2403
|
-
* @description
|
|
3111
|
+
* Z Index
|
|
3112
|
+
* @description Stacking order from bottom to top. The base image always has z_index 0.
|
|
2404
3113
|
*/
|
|
2405
|
-
|
|
3114
|
+
z_index: number;
|
|
2406
3115
|
}
|
|
2407
3116
|
|
|
2408
3117
|
export interface Seed2MiniMessage {
|
|
@@ -2581,6 +3290,60 @@ export interface SAM3DBodyAlignmentInfo {
|
|
|
2581
3290
|
translation: number[];
|
|
2582
3291
|
}
|
|
2583
3292
|
|
|
3293
|
+
export interface RodinGen25BbboxField {
|
|
3294
|
+
/**
|
|
3295
|
+
* Height
|
|
3296
|
+
* @description Height (y axis) dimension for the bounding box constraint.
|
|
3297
|
+
* @default 0
|
|
3298
|
+
*/
|
|
3299
|
+
height?: number;
|
|
3300
|
+
/**
|
|
3301
|
+
* Length
|
|
3302
|
+
* @description Length (z axis) dimension for the bounding box constraint.
|
|
3303
|
+
* @default 0
|
|
3304
|
+
*/
|
|
3305
|
+
length?: number;
|
|
3306
|
+
/**
|
|
3307
|
+
* Width
|
|
3308
|
+
* @description Width (x axis) dimension for the bounding box constraint.
|
|
3309
|
+
* @default 0
|
|
3310
|
+
*/
|
|
3311
|
+
width?: number;
|
|
3312
|
+
}
|
|
3313
|
+
|
|
3314
|
+
export interface RodinGen25Addons {
|
|
3315
|
+
/**
|
|
3316
|
+
* High Pack
|
|
3317
|
+
* @description Selecting HighPack generates 4K resolution texture instead of the default 2K. In Quad mode, the number of faces becomes ~16× the count set in the quality parameter.
|
|
3318
|
+
* @default false
|
|
3319
|
+
*/
|
|
3320
|
+
high_pack?: boolean;
|
|
3321
|
+
}
|
|
3322
|
+
|
|
3323
|
+
export interface RGBColor_2 {
|
|
3324
|
+
/**
|
|
3325
|
+
* B
|
|
3326
|
+
* @default 0
|
|
3327
|
+
*/
|
|
3328
|
+
b?: number;
|
|
3329
|
+
/**
|
|
3330
|
+
* G
|
|
3331
|
+
* @default 0
|
|
3332
|
+
*/
|
|
3333
|
+
g?: number;
|
|
3334
|
+
/**
|
|
3335
|
+
* R
|
|
3336
|
+
* @default 0
|
|
3337
|
+
*/
|
|
3338
|
+
r?: number;
|
|
3339
|
+
}
|
|
3340
|
+
|
|
3341
|
+
export interface RGBColor_1 {
|
|
3342
|
+
b: number;
|
|
3343
|
+
g: number;
|
|
3344
|
+
r: number;
|
|
3345
|
+
}
|
|
3346
|
+
|
|
2584
3347
|
export interface RGBColor {
|
|
2585
3348
|
/**
|
|
2586
3349
|
* B
|
|
@@ -2673,25 +3436,122 @@ export interface Region {
|
|
|
2673
3436
|
y2: number;
|
|
2674
3437
|
}
|
|
2675
3438
|
|
|
2676
|
-
export interface
|
|
3439
|
+
export interface ReferenceFace {
|
|
2677
3440
|
/**
|
|
2678
|
-
*
|
|
2679
|
-
* @description
|
|
3441
|
+
* Image Url
|
|
3442
|
+
* @description URL of the reference face image
|
|
2680
3443
|
*/
|
|
2681
|
-
|
|
3444
|
+
image_url: string;
|
|
3445
|
+
}
|
|
3446
|
+
|
|
3447
|
+
export interface ReferenceCondition {
|
|
2682
3448
|
/**
|
|
2683
|
-
*
|
|
2684
|
-
* @description
|
|
3449
|
+
* Type
|
|
3450
|
+
* @description Reference modality. Cross-modality list order is semantic.
|
|
3451
|
+
* @enum {string}
|
|
2685
3452
|
*/
|
|
2686
|
-
|
|
3453
|
+
type: 'image' | 'video' | 'audio';
|
|
3454
|
+
/**
|
|
3455
|
+
* Url
|
|
3456
|
+
* @description URL of the reference media.
|
|
3457
|
+
*/
|
|
3458
|
+
url: string;
|
|
2687
3459
|
}
|
|
2688
3460
|
|
|
2689
|
-
export interface
|
|
3461
|
+
export interface RayReframeSourcePosition {
|
|
2690
3462
|
/**
|
|
2691
|
-
*
|
|
2692
|
-
* @description
|
|
3463
|
+
* H Norm
|
|
3464
|
+
* @description Height of the source rectangle as a fraction of output height.
|
|
2693
3465
|
*/
|
|
2694
|
-
|
|
3466
|
+
h_norm: number;
|
|
3467
|
+
/**
|
|
3468
|
+
* W Norm
|
|
3469
|
+
* @description Width of the source rectangle as a fraction of output width.
|
|
3470
|
+
*/
|
|
3471
|
+
w_norm: number;
|
|
3472
|
+
/**
|
|
3473
|
+
* X Norm
|
|
3474
|
+
* @description Left edge of the source rectangle as a fraction of output width.
|
|
3475
|
+
*/
|
|
3476
|
+
x_norm: number;
|
|
3477
|
+
/**
|
|
3478
|
+
* Y Norm
|
|
3479
|
+
* @description Top edge of the source rectangle as a fraction of output height.
|
|
3480
|
+
*/
|
|
3481
|
+
y_norm: number;
|
|
3482
|
+
}
|
|
3483
|
+
|
|
3484
|
+
export interface RayEditTrajectoryControl {
|
|
3485
|
+
/**
|
|
3486
|
+
* Enabled
|
|
3487
|
+
* @description Enable motion-trajectory conditioning for the edit.
|
|
3488
|
+
* @default true
|
|
3489
|
+
*/
|
|
3490
|
+
enabled?: boolean;
|
|
3491
|
+
/**
|
|
3492
|
+
* Sparsity
|
|
3493
|
+
* @description Motion-trajectory sparsity. Higher values use fewer motion anchors. Leave unset for the default.
|
|
3494
|
+
*/
|
|
3495
|
+
sparsity?: number;
|
|
3496
|
+
}
|
|
3497
|
+
|
|
3498
|
+
export interface RayEditPoseControl {
|
|
3499
|
+
/**
|
|
3500
|
+
* Enabled
|
|
3501
|
+
* @description Enable pose / skeleton conditioning for the edit.
|
|
3502
|
+
* @default true
|
|
3503
|
+
*/
|
|
3504
|
+
enabled?: boolean;
|
|
3505
|
+
/**
|
|
3506
|
+
* Strength
|
|
3507
|
+
* @description Pose conditioning precision. 'precise' follows the source pose tightly; 'coarse' allows more freedom. Leave unset for the default.
|
|
3508
|
+
*/
|
|
3509
|
+
strength?: 'precise' | 'coarse';
|
|
3510
|
+
}
|
|
3511
|
+
|
|
3512
|
+
export interface RayEditNormalsControl {
|
|
3513
|
+
/**
|
|
3514
|
+
* Augmentation
|
|
3515
|
+
* @description Surface-normals augmentation. Higher values allow more reinterpretation of surface geometry. Leave unset for the default.
|
|
3516
|
+
*/
|
|
3517
|
+
augmentation?: number;
|
|
3518
|
+
/**
|
|
3519
|
+
* Enabled
|
|
3520
|
+
* @description Enable surface-normals conditioning for the edit.
|
|
3521
|
+
* @default true
|
|
3522
|
+
*/
|
|
3523
|
+
enabled?: boolean;
|
|
3524
|
+
}
|
|
3525
|
+
|
|
3526
|
+
export interface RayEditFaceControl {
|
|
3527
|
+
/**
|
|
3528
|
+
* Enabled
|
|
3529
|
+
* @description Enable face-identity conditioning for the edit.
|
|
3530
|
+
* @default true
|
|
3531
|
+
*/
|
|
3532
|
+
enabled?: boolean;
|
|
3533
|
+
}
|
|
3534
|
+
|
|
3535
|
+
export interface RayEditDepthControl {
|
|
3536
|
+
/**
|
|
3537
|
+
* Blur
|
|
3538
|
+
* @description Depth blur. Higher values allow more geometric freedom. Leave unset for the default.
|
|
3539
|
+
*/
|
|
3540
|
+
blur?: number;
|
|
3541
|
+
/**
|
|
3542
|
+
* Enabled
|
|
3543
|
+
* @description Enable depth / scene-geometry conditioning for the edit.
|
|
3544
|
+
* @default true
|
|
3545
|
+
*/
|
|
3546
|
+
enabled?: boolean;
|
|
3547
|
+
}
|
|
3548
|
+
|
|
3549
|
+
export interface RayEditControls {
|
|
3550
|
+
depth?: RayEditDepthControl;
|
|
3551
|
+
face?: RayEditFaceControl;
|
|
3552
|
+
normals?: RayEditNormalsControl;
|
|
3553
|
+
pose?: RayEditPoseControl;
|
|
3554
|
+
trajectory?: RayEditTrajectoryControl;
|
|
2695
3555
|
}
|
|
2696
3556
|
|
|
2697
3557
|
export interface RawImage {
|
|
@@ -2915,6 +3775,24 @@ export interface PromptObject {
|
|
|
2915
3775
|
texture?: string;
|
|
2916
3776
|
}
|
|
2917
3777
|
|
|
3778
|
+
export interface PresetCustomization {
|
|
3779
|
+
/**
|
|
3780
|
+
* Position
|
|
3781
|
+
* @description Vertical placement of static subtitles on screen.
|
|
3782
|
+
*/
|
|
3783
|
+
position?: 'top' | 'center' | 'bottom';
|
|
3784
|
+
/**
|
|
3785
|
+
* Shadow
|
|
3786
|
+
* @description Improves readability over bright or busy backgrounds.
|
|
3787
|
+
*/
|
|
3788
|
+
shadow?: 'none' | 'min' | 'mid' | 'max';
|
|
3789
|
+
/**
|
|
3790
|
+
* Text customizations
|
|
3791
|
+
* @description Per-tier text styling for baseline and highlighted words.
|
|
3792
|
+
*/
|
|
3793
|
+
text_customizations?: TextCustomizations;
|
|
3794
|
+
}
|
|
3795
|
+
|
|
2918
3796
|
export interface PolygonOutput {
|
|
2919
3797
|
/**
|
|
2920
3798
|
* Polygons
|
|
@@ -2946,7 +3824,7 @@ export interface PointPromptBase {
|
|
|
2946
3824
|
label?: 0 | 1;
|
|
2947
3825
|
/**
|
|
2948
3826
|
* Object Id
|
|
2949
|
-
* @description Optional object identifier. Prompts sharing an object id refine the same object.
|
|
3827
|
+
* @description Optional object identifier. Prompts sharing an object id refine the same object. When a text prompt is also given, the id selects which detected object the points refine.
|
|
2950
3828
|
*/
|
|
2951
3829
|
object_id?: number;
|
|
2952
3830
|
/**
|
|
@@ -3002,7 +3880,7 @@ export interface PointPrompt {
|
|
|
3002
3880
|
label?: 0 | 1;
|
|
3003
3881
|
/**
|
|
3004
3882
|
* Object Id
|
|
3005
|
-
* @description Optional object identifier. Prompts sharing an object id refine the same object.
|
|
3883
|
+
* @description Optional object identifier. Prompts sharing an object id refine the same object. When a text prompt is also given, the id selects which detected object the points refine.
|
|
3006
3884
|
*/
|
|
3007
3885
|
object_id?: number;
|
|
3008
3886
|
/**
|
|
@@ -3020,12 +3898,12 @@ export interface PointPrompt {
|
|
|
3020
3898
|
export interface Point_1 {
|
|
3021
3899
|
/**
|
|
3022
3900
|
* X
|
|
3023
|
-
* @description
|
|
3901
|
+
* @description The x coordinate.
|
|
3024
3902
|
*/
|
|
3025
3903
|
x: number;
|
|
3026
3904
|
/**
|
|
3027
3905
|
* Y
|
|
3028
|
-
* @description
|
|
3906
|
+
* @description The y coordinate.
|
|
3029
3907
|
*/
|
|
3030
3908
|
y: number;
|
|
3031
3909
|
}
|
|
@@ -3033,16 +3911,30 @@ export interface Point_1 {
|
|
|
3033
3911
|
export interface Point {
|
|
3034
3912
|
/**
|
|
3035
3913
|
* X
|
|
3036
|
-
* @description
|
|
3914
|
+
* @description X coordinate of the point in normalized format (0 to 1)
|
|
3037
3915
|
*/
|
|
3038
3916
|
x: number;
|
|
3039
3917
|
/**
|
|
3040
3918
|
* Y
|
|
3041
|
-
* @description
|
|
3919
|
+
* @description Y coordinate of the point in normalized format (0 to 1)
|
|
3042
3920
|
*/
|
|
3043
3921
|
y: number;
|
|
3044
3922
|
}
|
|
3045
3923
|
|
|
3924
|
+
export interface PodcastConversation {
|
|
3925
|
+
/**
|
|
3926
|
+
* Text
|
|
3927
|
+
* @description Text spoken in this conversation turn, up to 400 characters.
|
|
3928
|
+
*/
|
|
3929
|
+
text: string;
|
|
3930
|
+
/**
|
|
3931
|
+
* Voice
|
|
3932
|
+
* @description Built-in voice used for this conversation turn.
|
|
3933
|
+
* @enum {string}
|
|
3934
|
+
*/
|
|
3935
|
+
voice: 'Ethan' | 'Victoria' | 'Jake' | 'Luna' | 'Emma';
|
|
3936
|
+
}
|
|
3937
|
+
|
|
3046
3938
|
export interface PhotographicCharacteristicsDetails {
|
|
3047
3939
|
/**
|
|
3048
3940
|
* Camera Angle
|
|
@@ -3066,7 +3958,7 @@ export interface PhotographicCharacteristicsDetails {
|
|
|
3066
3958
|
lens_focal_length: string;
|
|
3067
3959
|
}
|
|
3068
3960
|
|
|
3069
|
-
export
|
|
3961
|
+
export interface PhotographicCharacteristics_1 {
|
|
3070
3962
|
/**
|
|
3071
3963
|
* Camera Angle
|
|
3072
3964
|
* @description The angle of the camera in the image to be generated.
|
|
@@ -3087,9 +3979,8 @@ export type PhotographicCharacteristics_1 = {
|
|
|
3087
3979
|
* @description The focal length of the lens in the image to be generated.
|
|
3088
3980
|
*/
|
|
3089
3981
|
lens_focal_length?: string;
|
|
3090
|
-
|
|
3091
|
-
|
|
3092
|
-
};
|
|
3982
|
+
[key: string]: any;
|
|
3983
|
+
}
|
|
3093
3984
|
|
|
3094
3985
|
export interface PhotographicCharacteristics {
|
|
3095
3986
|
/**
|
|
@@ -3114,7 +4005,7 @@ export interface PhotographicCharacteristics {
|
|
|
3114
4005
|
lens_focal_length?: string;
|
|
3115
4006
|
}
|
|
3116
4007
|
|
|
3117
|
-
export interface
|
|
4008
|
+
export interface OutputFormat_1 {
|
|
3118
4009
|
/**
|
|
3119
4010
|
* Bit Rate
|
|
3120
4011
|
* @description Bit rate in bps. Only applicable for MP3 codec. Defaults to 128000 for MP3.
|
|
@@ -3126,14 +4017,53 @@ export interface OutputFormat {
|
|
|
3126
4017
|
* @default mp3
|
|
3127
4018
|
* @enum {string}
|
|
3128
4019
|
*/
|
|
3129
|
-
codec?: 'mp3' | 'wav' | 'pcm' | 'mulaw' | 'alaw';
|
|
4020
|
+
codec?: 'mp3' | 'wav' | 'pcm' | 'mulaw' | 'alaw';
|
|
4021
|
+
/**
|
|
4022
|
+
* Sample Rate
|
|
4023
|
+
* @description Sample rate in Hz.
|
|
4024
|
+
* @default 24000
|
|
4025
|
+
* @enum {integer}
|
|
4026
|
+
*/
|
|
4027
|
+
sample_rate?: 8000 | 16000 | 22050 | 24000 | 44100 | 48000;
|
|
4028
|
+
}
|
|
4029
|
+
|
|
4030
|
+
export interface OutputFormat {
|
|
4031
|
+
/**
|
|
4032
|
+
* Bit Rate
|
|
4033
|
+
* @description Output bit rate. Only used when container is 'mp3'.
|
|
4034
|
+
*/
|
|
4035
|
+
bit_rate?: number;
|
|
4036
|
+
/**
|
|
4037
|
+
* Container
|
|
4038
|
+
* @description Output audio container format.
|
|
4039
|
+
* @default mp3
|
|
4040
|
+
* @enum {string}
|
|
4041
|
+
*/
|
|
4042
|
+
container?: 'mp3' | 'raw';
|
|
4043
|
+
/**
|
|
4044
|
+
* Encoding
|
|
4045
|
+
* @description PCM encoding. Only used when container is 'raw'.
|
|
4046
|
+
*/
|
|
4047
|
+
encoding?: 'pcm_s16le' | 'pcm_f32le' | 'pcm_mulaw';
|
|
3130
4048
|
/**
|
|
3131
4049
|
* Sample Rate
|
|
3132
|
-
* @description
|
|
3133
|
-
* @default
|
|
3134
|
-
* @enum {integer}
|
|
4050
|
+
* @description Output sample rate in Hz.
|
|
4051
|
+
* @default 44100
|
|
3135
4052
|
*/
|
|
3136
|
-
sample_rate?:
|
|
4053
|
+
sample_rate?: number;
|
|
4054
|
+
}
|
|
4055
|
+
|
|
4056
|
+
export interface OutpaintValidation {
|
|
4057
|
+
/**
|
|
4058
|
+
* Prompt
|
|
4059
|
+
* @description The prompt to use for validation.
|
|
4060
|
+
*/
|
|
4061
|
+
prompt: string;
|
|
4062
|
+
/**
|
|
4063
|
+
* Video Url
|
|
4064
|
+
* @description URL to the full-canvas video whose surround should be outpainted.
|
|
4065
|
+
*/
|
|
4066
|
+
video_url: string;
|
|
3137
4067
|
}
|
|
3138
4068
|
|
|
3139
4069
|
export interface OmniVideoElementInput {
|
|
@@ -3141,7 +4071,7 @@ export interface OmniVideoElementInput {
|
|
|
3141
4071
|
* Frontal Image Url
|
|
3142
4072
|
* @description The frontal image of the element (main view).
|
|
3143
4073
|
*
|
|
3144
|
-
* Max file size:
|
|
4074
|
+
* Max file size: 50.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s
|
|
3145
4075
|
*/
|
|
3146
4076
|
frontal_image_url: string;
|
|
3147
4077
|
/**
|
|
@@ -3260,6 +4190,65 @@ export interface Object {
|
|
|
3260
4190
|
y_min: number;
|
|
3261
4191
|
}
|
|
3262
4192
|
|
|
4193
|
+
export interface NemotronDiffusionVLMUsage {
|
|
4194
|
+
/**
|
|
4195
|
+
* Completion Tokens
|
|
4196
|
+
* @description Number of generated completion tokens.
|
|
4197
|
+
*/
|
|
4198
|
+
completion_tokens: number;
|
|
4199
|
+
/**
|
|
4200
|
+
* Num Function Evals
|
|
4201
|
+
* @description Number of model function evaluations used for generation.
|
|
4202
|
+
*/
|
|
4203
|
+
num_function_evals: number;
|
|
4204
|
+
/**
|
|
4205
|
+
* Prompt Tokens
|
|
4206
|
+
* @description Number of prompt tokens sent to the model.
|
|
4207
|
+
*/
|
|
4208
|
+
prompt_tokens: number;
|
|
4209
|
+
}
|
|
4210
|
+
|
|
4211
|
+
export interface NemotronDiffusionVLMTimings {
|
|
4212
|
+
/**
|
|
4213
|
+
* Decode Time
|
|
4214
|
+
* @description Time spent decoding output token IDs to text.
|
|
4215
|
+
*/
|
|
4216
|
+
decode_time: number;
|
|
4217
|
+
/**
|
|
4218
|
+
* Generation Time
|
|
4219
|
+
* @description Time spent inside model generation.
|
|
4220
|
+
*/
|
|
4221
|
+
generation_time: number;
|
|
4222
|
+
/**
|
|
4223
|
+
* GPU Transfer Time
|
|
4224
|
+
* @description Time spent moving tensors to the GPU.
|
|
4225
|
+
*/
|
|
4226
|
+
gpu_transfer_time: number;
|
|
4227
|
+
/**
|
|
4228
|
+
* Image Validation Time
|
|
4229
|
+
* @description Time spent validating and loading the input image.
|
|
4230
|
+
*/
|
|
4231
|
+
image_validation_time: number;
|
|
4232
|
+
/**
|
|
4233
|
+
* Preprocessing Time
|
|
4234
|
+
* @description Time spent expanding the chat template and preprocessing tensors.
|
|
4235
|
+
*/
|
|
4236
|
+
preprocessing_time: number;
|
|
4237
|
+
/**
|
|
4238
|
+
* Total Time
|
|
4239
|
+
* @description Total request time in seconds.
|
|
4240
|
+
*/
|
|
4241
|
+
total_time: number;
|
|
4242
|
+
}
|
|
4243
|
+
|
|
4244
|
+
export interface MusicV2CompositionPlan {
|
|
4245
|
+
/**
|
|
4246
|
+
* Chunks
|
|
4247
|
+
* @description The chunks that make up the generation, in order. At most 30 chunks, totalling between 3000ms and 600000ms.
|
|
4248
|
+
*/
|
|
4249
|
+
chunks: MusicGenerationChunk[];
|
|
4250
|
+
}
|
|
4251
|
+
|
|
3263
4252
|
export interface MusicSection {
|
|
3264
4253
|
/**
|
|
3265
4254
|
* Duration Ms
|
|
@@ -3288,6 +4277,43 @@ export interface MusicSection {
|
|
|
3288
4277
|
section_name: string;
|
|
3289
4278
|
}
|
|
3290
4279
|
|
|
4280
|
+
export interface MusicGenerationChunk {
|
|
4281
|
+
audio_reference?: MusicAudioReference;
|
|
4282
|
+
/**
|
|
4283
|
+
* Context Adherence
|
|
4284
|
+
* @description How closely this chunk follows the context of its surrounding chunks. Low adherence lets the model deviate and be more creative, high adherence keeps it consistent with the surrounding context.
|
|
4285
|
+
*/
|
|
4286
|
+
context_adherence?: 'low' | 'medium' | 'high';
|
|
4287
|
+
/**
|
|
4288
|
+
* Duration Ms
|
|
4289
|
+
* @description The duration of the chunk in milliseconds. Must be between 3000ms and 120000ms.
|
|
4290
|
+
*/
|
|
4291
|
+
duration_ms: number;
|
|
4292
|
+
/**
|
|
4293
|
+
* Negative Styles
|
|
4294
|
+
* @description The styles and musical directions that should not be present in this chunk. Leaving this empty is a good default; only set it to explicitly avoid a particular style or direction.
|
|
4295
|
+
*/
|
|
4296
|
+
negative_styles?: string[];
|
|
4297
|
+
/**
|
|
4298
|
+
* Positive Styles
|
|
4299
|
+
* @description The styles and musical directions that should be present in this chunk. Use English for best results. The styles of the first chunk matter most as they set the overall tone and genre; later chunks can add nuance, progression or change direction.
|
|
4300
|
+
* @example [
|
|
4301
|
+
* "synthwave",
|
|
4302
|
+
* "analog drum machine",
|
|
4303
|
+
* "great production quality"
|
|
4304
|
+
* ]
|
|
4305
|
+
*/
|
|
4306
|
+
positive_styles: string[];
|
|
4307
|
+
/**
|
|
4308
|
+
* Text
|
|
4309
|
+
* @description The text to generate for this chunk. Can start with an optional section name in square brackets, e.g. [Verse 1], followed by lyric lines, plus inline directions in curly braces, e.g. {scratching}. Section names must be between 1 and 100 characters. At most 30 lines are allowed, each at most 200 characters.
|
|
4310
|
+
* @example [Verse 1]
|
|
4311
|
+
* Neon rain on empty streets
|
|
4312
|
+
* I keep walking to the beat
|
|
4313
|
+
*/
|
|
4314
|
+
text: string;
|
|
4315
|
+
}
|
|
4316
|
+
|
|
3291
4317
|
export interface MusicCompositionPlan {
|
|
3292
4318
|
/**
|
|
3293
4319
|
* Negative Global Styles
|
|
@@ -3306,6 +4332,31 @@ export interface MusicCompositionPlan {
|
|
|
3306
4332
|
sections: MusicSection[];
|
|
3307
4333
|
}
|
|
3308
4334
|
|
|
4335
|
+
export interface MusicAudioReference {
|
|
4336
|
+
/**
|
|
4337
|
+
* Audio Url
|
|
4338
|
+
* @description URL of the audio clip to use as the style reference.
|
|
4339
|
+
* @example https://storage.googleapis.com/falserverless/example_outputs/elevenlabs/music_generated.mp3
|
|
4340
|
+
*/
|
|
4341
|
+
audio_url: string;
|
|
4342
|
+
/**
|
|
4343
|
+
* End Ms
|
|
4344
|
+
* @description Offset into the clip where the referenced window ends, in milliseconds. Defaults to 30000ms after start_ms, or the end of the clip if it is shorter. The window must be at most 30000ms long.
|
|
4345
|
+
*/
|
|
4346
|
+
end_ms?: number;
|
|
4347
|
+
/**
|
|
4348
|
+
* Start Ms
|
|
4349
|
+
* @description Offset into the clip where the referenced window starts, in milliseconds.
|
|
4350
|
+
* @default 0
|
|
4351
|
+
*/
|
|
4352
|
+
start_ms?: number;
|
|
4353
|
+
/**
|
|
4354
|
+
* Strength
|
|
4355
|
+
* @description How strongly the model follows the reference. Low lets it deviate and be more creative, high keeps it close to the reference.
|
|
4356
|
+
*/
|
|
4357
|
+
strength?: 'low' | 'medium' | 'high' | 'xhigh';
|
|
4358
|
+
}
|
|
4359
|
+
|
|
3309
4360
|
export interface MoondreamInputParam {
|
|
3310
4361
|
/**
|
|
3311
4362
|
* Image URL
|
|
@@ -3322,6 +4373,20 @@ export interface MoondreamInputParam {
|
|
|
3322
4373
|
prompt?: string;
|
|
3323
4374
|
}
|
|
3324
4375
|
|
|
4376
|
+
export interface Moodboard {
|
|
4377
|
+
/**
|
|
4378
|
+
* Id
|
|
4379
|
+
* @description Krea moodboard identifier (UUID).
|
|
4380
|
+
*/
|
|
4381
|
+
id: string;
|
|
4382
|
+
/**
|
|
4383
|
+
* Strength
|
|
4384
|
+
* @description How strongly the moodboard influences the generated image.
|
|
4385
|
+
* @default 0.23
|
|
4386
|
+
*/
|
|
4387
|
+
strength?: number;
|
|
4388
|
+
}
|
|
4389
|
+
|
|
3325
4390
|
export interface ModelUrls_3 {
|
|
3326
4391
|
fbx?: File;
|
|
3327
4392
|
glb?: File;
|
|
@@ -3330,12 +4395,6 @@ export interface ModelUrls_3 {
|
|
|
3330
4395
|
}
|
|
3331
4396
|
|
|
3332
4397
|
export interface ModelUrls_2 {
|
|
3333
|
-
base_model?: File;
|
|
3334
|
-
glb?: File;
|
|
3335
|
-
pbr_model?: File;
|
|
3336
|
-
}
|
|
3337
|
-
|
|
3338
|
-
export interface ModelUrls_1 {
|
|
3339
4398
|
fbx?: File;
|
|
3340
4399
|
glb?: File;
|
|
3341
4400
|
mtl?: File;
|
|
@@ -3344,6 +4403,25 @@ export interface ModelUrls_1 {
|
|
|
3344
4403
|
usdz?: File;
|
|
3345
4404
|
}
|
|
3346
4405
|
|
|
4406
|
+
export interface ModelUrls_1 {
|
|
4407
|
+
base_model?: File;
|
|
4408
|
+
/**
|
|
4409
|
+
* FBX
|
|
4410
|
+
* @description FBX format 3D model
|
|
4411
|
+
*/
|
|
4412
|
+
fbx?: File;
|
|
4413
|
+
/**
|
|
4414
|
+
* GLB
|
|
4415
|
+
* @description GLB format 3D model
|
|
4416
|
+
*/
|
|
4417
|
+
glb?: File;
|
|
4418
|
+
/**
|
|
4419
|
+
* PBR Model
|
|
4420
|
+
* @description PBR-textured model
|
|
4421
|
+
*/
|
|
4422
|
+
pbr_model?: File;
|
|
4423
|
+
}
|
|
4424
|
+
|
|
3347
4425
|
export interface ModelUrls {
|
|
3348
4426
|
blend?: File;
|
|
3349
4427
|
fbx?: File;
|
|
@@ -3371,6 +4449,36 @@ export interface MaskMetadata {
|
|
|
3371
4449
|
score?: number;
|
|
3372
4450
|
}
|
|
3373
4451
|
|
|
4452
|
+
export interface Margin {
|
|
4453
|
+
/**
|
|
4454
|
+
* All
|
|
4455
|
+
* @description Margin applied to all sides. '%' (0–49%) of the canvas dimension, or 'px' (>=0px).
|
|
4456
|
+
* @default 20%
|
|
4457
|
+
* @example 20%
|
|
4458
|
+
*/
|
|
4459
|
+
all?: string;
|
|
4460
|
+
/**
|
|
4461
|
+
* Bottom
|
|
4462
|
+
* @description Bottom-side override of `all`. '%' (0–49%) or 'px' (>=0px).
|
|
4463
|
+
*/
|
|
4464
|
+
bottom?: string;
|
|
4465
|
+
/**
|
|
4466
|
+
* Left
|
|
4467
|
+
* @description Left-side override of `all`. '%' (0–49%) or 'px' (>=0px).
|
|
4468
|
+
*/
|
|
4469
|
+
left?: string;
|
|
4470
|
+
/**
|
|
4471
|
+
* Right
|
|
4472
|
+
* @description Right-side override of `all`. '%' (0–49%) or 'px' (>=0px).
|
|
4473
|
+
*/
|
|
4474
|
+
right?: string;
|
|
4475
|
+
/**
|
|
4476
|
+
* Top
|
|
4477
|
+
* @description Top-side override of `all`. '%' (0–49%) or 'px' (>=0px).
|
|
4478
|
+
*/
|
|
4479
|
+
top?: string;
|
|
4480
|
+
}
|
|
4481
|
+
|
|
3374
4482
|
export interface MapImageFile {
|
|
3375
4483
|
/**
|
|
3376
4484
|
* Content Type
|
|
@@ -3413,6 +4521,26 @@ export interface MapImageFile {
|
|
|
3413
4521
|
width?: number;
|
|
3414
4522
|
}
|
|
3415
4523
|
|
|
4524
|
+
export interface LyricsWord {
|
|
4525
|
+
end?: number;
|
|
4526
|
+
start?: number;
|
|
4527
|
+
text?: string;
|
|
4528
|
+
}
|
|
4529
|
+
|
|
4530
|
+
export interface LyricsSection {
|
|
4531
|
+
end?: number;
|
|
4532
|
+
lines?: LyricsLine[];
|
|
4533
|
+
section_type?: 'intro' | 'verse' | 'pre-chorus' | 'chorus' | 'bridge' | 'break' | 'outro';
|
|
4534
|
+
start?: number;
|
|
4535
|
+
}
|
|
4536
|
+
|
|
4537
|
+
export interface LyricsLine {
|
|
4538
|
+
end?: number;
|
|
4539
|
+
start?: number;
|
|
4540
|
+
text?: string;
|
|
4541
|
+
words?: LyricsWord[];
|
|
4542
|
+
}
|
|
4543
|
+
|
|
3416
4544
|
export interface LoudnormSummary {
|
|
3417
4545
|
/**
|
|
3418
4546
|
* Input Integrated
|
|
@@ -3493,30 +4621,23 @@ export interface LoudnessNormalizationSetting {
|
|
|
3493
4621
|
target_range?: number;
|
|
3494
4622
|
}
|
|
3495
4623
|
|
|
3496
|
-
export interface
|
|
3497
|
-
/**
|
|
3498
|
-
* Force
|
|
3499
|
-
* @description If set to true, the embedding will be forced to be used.
|
|
3500
|
-
* @default false
|
|
3501
|
-
*/
|
|
3502
|
-
force?: boolean;
|
|
4624
|
+
export interface LoraWeight_4 {
|
|
3503
4625
|
/**
|
|
3504
4626
|
* Path
|
|
3505
|
-
* @description URL or path to
|
|
3506
|
-
* @example https://
|
|
3507
|
-
* @example https://filebin.net/3chfqasxpqu21y8n/my-custom-lora-v1.safetensors
|
|
4627
|
+
* @description URL or the path to the LoRA weights.
|
|
4628
|
+
* @example https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors
|
|
3508
4629
|
*/
|
|
3509
4630
|
path: string;
|
|
3510
4631
|
/**
|
|
3511
4632
|
* Scale
|
|
3512
4633
|
* @description The scale of the LoRA weight. This is used to scale the LoRA weight
|
|
3513
4634
|
* before merging it with the base model.
|
|
3514
|
-
* @default 1
|
|
4635
|
+
* @default 0.1
|
|
3515
4636
|
*/
|
|
3516
4637
|
scale?: number;
|
|
3517
4638
|
}
|
|
3518
4639
|
|
|
3519
|
-
export interface
|
|
4640
|
+
export interface LoraWeight_3 {
|
|
3520
4641
|
/**
|
|
3521
4642
|
* Path
|
|
3522
4643
|
* @description URL or the path to the LoRA weights.
|
|
@@ -3536,39 +4657,6 @@ export interface LoraWeight_5 {
|
|
|
3536
4657
|
weight_name?: string;
|
|
3537
4658
|
}
|
|
3538
4659
|
|
|
3539
|
-
export interface LoraWeight_4 {
|
|
3540
|
-
/**
|
|
3541
|
-
* Path
|
|
3542
|
-
* @description URL or the path to the LoRA weights.
|
|
3543
|
-
* @example https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors
|
|
3544
|
-
*/
|
|
3545
|
-
path: string;
|
|
3546
|
-
/**
|
|
3547
|
-
* Scale
|
|
3548
|
-
* @description The scale of the LoRA weight. This is used to scale the LoRA weight
|
|
3549
|
-
* before merging it with the base model.
|
|
3550
|
-
* @default 0.1
|
|
3551
|
-
*/
|
|
3552
|
-
scale?: number;
|
|
3553
|
-
}
|
|
3554
|
-
|
|
3555
|
-
export interface LoraWeight_3 {
|
|
3556
|
-
/**
|
|
3557
|
-
* Path
|
|
3558
|
-
* @description URL or the path to the LoRA weights. Or HF model name.
|
|
3559
|
-
* @example https://civitai.com/api/download/models/135931
|
|
3560
|
-
* @example https://filebin.net/3chfqasxpqu21y8n/my-custom-lora-v1.safetensors
|
|
3561
|
-
*/
|
|
3562
|
-
path: string;
|
|
3563
|
-
/**
|
|
3564
|
-
* Scale
|
|
3565
|
-
* @description The scale of the LoRA weight. This is used to scale the LoRA weight
|
|
3566
|
-
* before merging it with the base model.
|
|
3567
|
-
* @default 1
|
|
3568
|
-
*/
|
|
3569
|
-
scale?: number;
|
|
3570
|
-
}
|
|
3571
|
-
|
|
3572
4660
|
export interface LoraWeight_2 {
|
|
3573
4661
|
/**
|
|
3574
4662
|
* Path
|
|
@@ -3581,7 +4669,11 @@ export interface LoraWeight_2 {
|
|
|
3581
4669
|
* before merging it with the base model. Providing a dictionary as {"layer_name":layer_scale} allows per-layer lora scale settings. Layers with no scale provided will have scale 1.0.
|
|
3582
4670
|
* @default 1
|
|
3583
4671
|
*/
|
|
3584
|
-
scale?:
|
|
4672
|
+
scale?:
|
|
4673
|
+
| {
|
|
4674
|
+
[key: string]: number;
|
|
4675
|
+
}
|
|
4676
|
+
| number;
|
|
3585
4677
|
}
|
|
3586
4678
|
|
|
3587
4679
|
export interface LoRAWeight_1 {
|
|
@@ -3620,7 +4712,7 @@ export interface LoraWeight_1 {
|
|
|
3620
4712
|
force?: boolean;
|
|
3621
4713
|
/**
|
|
3622
4714
|
* Path
|
|
3623
|
-
* @description URL or
|
|
4715
|
+
* @description URL or path to a LoRA safetensors file. Or HF model name that resolves to safetensors weights.
|
|
3624
4716
|
* @example https://civitai.com/api/download/models/135931
|
|
3625
4717
|
* @example https://filebin.net/3chfqasxpqu21y8n/my-custom-lora-v1.safetensors
|
|
3626
4718
|
*/
|
|
@@ -3668,7 +4760,55 @@ export interface LoraWeight {
|
|
|
3668
4760
|
scale?: number;
|
|
3669
4761
|
}
|
|
3670
4762
|
|
|
3671
|
-
export interface
|
|
4763
|
+
export interface LoraTrainingFailure {
|
|
4764
|
+
/**
|
|
4765
|
+
* Denoiser
|
|
4766
|
+
* @description TRELLIS.2 denoiser whose training did not complete.
|
|
4767
|
+
* @enum {string}
|
|
4768
|
+
*/
|
|
4769
|
+
denoiser: 'sparse_structure' | 'geometry' | 'texture';
|
|
4770
|
+
/**
|
|
4771
|
+
* Error
|
|
4772
|
+
* @description Reason the training did not complete.
|
|
4773
|
+
*/
|
|
4774
|
+
error: string;
|
|
4775
|
+
}
|
|
4776
|
+
|
|
4777
|
+
export interface LoRAInput_5 {
|
|
4778
|
+
/**
|
|
4779
|
+
* Path
|
|
4780
|
+
* @description URL or HuggingFace repo id (owner/repo) of the LoRA weights.
|
|
4781
|
+
* @example https://huggingface.co/owner/repo/resolve/main/lora.safetensors
|
|
4782
|
+
*/
|
|
4783
|
+
path: string;
|
|
4784
|
+
/**
|
|
4785
|
+
* Scale
|
|
4786
|
+
* @description Strength of the LoRA (0.0 to 4.0).
|
|
4787
|
+
* @default 1
|
|
4788
|
+
*/
|
|
4789
|
+
scale?: number;
|
|
4790
|
+
/**
|
|
4791
|
+
* Weight Name
|
|
4792
|
+
* @description Name of the LoRA weight file. Only used when `path` is a HuggingFace repo and it holds more than one LoRA.
|
|
4793
|
+
*/
|
|
4794
|
+
weight_name?: string;
|
|
4795
|
+
}
|
|
4796
|
+
|
|
4797
|
+
export interface LoRAInput_4 {
|
|
4798
|
+
/**
|
|
4799
|
+
* Path
|
|
4800
|
+
* @description URL to an Ideogram V4 LoRA weights file (.safetensors).
|
|
4801
|
+
*/
|
|
4802
|
+
path: string;
|
|
4803
|
+
/**
|
|
4804
|
+
* Scale
|
|
4805
|
+
* @description Scale factor for the LoRA weights.
|
|
4806
|
+
* @default 1
|
|
4807
|
+
*/
|
|
4808
|
+
scale?: number;
|
|
4809
|
+
}
|
|
4810
|
+
|
|
4811
|
+
export interface LoRAInput_3 {
|
|
3672
4812
|
/**
|
|
3673
4813
|
* Path
|
|
3674
4814
|
* @description URL, HuggingFace repo ID (owner/repo) to lora weights.
|
|
@@ -3682,10 +4822,32 @@ export interface LoRAInput_2 {
|
|
|
3682
4822
|
scale?: number;
|
|
3683
4823
|
}
|
|
3684
4824
|
|
|
4825
|
+
export interface LoRAInput_2 {
|
|
4826
|
+
/**
|
|
4827
|
+
* Path
|
|
4828
|
+
* @description Direct HTTP(S) download URL of the LoRA file (.safetensors). The file is downloaded through an SSRF-safe downloader before it is loaded. Max size: 3 GB.
|
|
4829
|
+
* @example https://example.com/path/to/lora.safetensors
|
|
4830
|
+
*/
|
|
4831
|
+
path: string;
|
|
4832
|
+
/**
|
|
4833
|
+
* Scale
|
|
4834
|
+
* @description Strength of the LoRA application (0.0 to 2.0). Higher values = stronger effect on the generated video.
|
|
4835
|
+
* @default 1
|
|
4836
|
+
*/
|
|
4837
|
+
scale?: number;
|
|
4838
|
+
/**
|
|
4839
|
+
* Transformer
|
|
4840
|
+
* @description Forward-compatibility flag for multi-transformer architectures. LTX-2.3 has a single transformer, so 'both' is the right choice for almost all users.
|
|
4841
|
+
* @default both
|
|
4842
|
+
* @enum {string}
|
|
4843
|
+
*/
|
|
4844
|
+
transformer?: 'high' | 'low' | 'both';
|
|
4845
|
+
}
|
|
4846
|
+
|
|
3685
4847
|
export interface LoRAInput_1 {
|
|
3686
4848
|
/**
|
|
3687
4849
|
* Path
|
|
3688
|
-
* @description URL, HuggingFace repo ID (owner/repo)
|
|
4850
|
+
* @description URL, HuggingFace repo ID (owner/repo) to lora weights.
|
|
3689
4851
|
*/
|
|
3690
4852
|
path: string;
|
|
3691
4853
|
/**
|
|
@@ -3694,25 +4856,57 @@ export interface LoRAInput_1 {
|
|
|
3694
4856
|
* @default 1
|
|
3695
4857
|
*/
|
|
3696
4858
|
scale?: number;
|
|
4859
|
+
/**
|
|
4860
|
+
* Weight Name
|
|
4861
|
+
* @description Name of the LoRA weight. Only used if `path` is a HuggingFace repository, and is only required when the repository contains multiple LoRA weights.
|
|
4862
|
+
*/
|
|
4863
|
+
weight_name?: string;
|
|
3697
4864
|
}
|
|
3698
4865
|
|
|
3699
4866
|
export interface LoRAInput {
|
|
3700
4867
|
/**
|
|
3701
4868
|
* Path
|
|
3702
|
-
* @description URL, HuggingFace repo ID (owner/repo) to
|
|
4869
|
+
* @description URL, HuggingFace repo ID (owner/repo), or local path to LoRA weights.
|
|
3703
4870
|
*/
|
|
3704
4871
|
path: string;
|
|
3705
4872
|
/**
|
|
3706
|
-
* Scale
|
|
3707
|
-
* @description Scale factor for LoRA application (0.0 to 4.0).
|
|
3708
|
-
* @default 1
|
|
4873
|
+
* Scale
|
|
4874
|
+
* @description Scale factor for LoRA application (0.0 to 4.0).
|
|
4875
|
+
* @default 1
|
|
4876
|
+
*/
|
|
4877
|
+
scale?: number;
|
|
4878
|
+
}
|
|
4879
|
+
|
|
4880
|
+
export interface LoraAdapterResult {
|
|
4881
|
+
/**
|
|
4882
|
+
* Denoiser
|
|
4883
|
+
* @description TRELLIS.2 denoiser this LoRA adapter was trained for: sparse_structure, geometry, or texture.
|
|
4884
|
+
* @enum {string}
|
|
4885
|
+
*/
|
|
4886
|
+
denoiser: 'sparse_structure' | 'geometry' | 'texture';
|
|
4887
|
+
/**
|
|
4888
|
+
* Learning Rate
|
|
4889
|
+
* @description Learning rate used for LoRA optimization.
|
|
4890
|
+
*/
|
|
4891
|
+
learning_rate: number;
|
|
4892
|
+
lora_file: File;
|
|
4893
|
+
/**
|
|
4894
|
+
* Rank
|
|
4895
|
+
* @description LoRA rank used for training.
|
|
4896
|
+
* @enum {integer}
|
|
4897
|
+
*/
|
|
4898
|
+
rank: 16 | 32 | 64;
|
|
4899
|
+
/**
|
|
4900
|
+
* Resolution
|
|
4901
|
+
* @description Resolution this LoRA adapter was trained at. Use the same resolution in trellis-2-lora inference.
|
|
4902
|
+
* @enum {integer}
|
|
3709
4903
|
*/
|
|
3710
|
-
|
|
4904
|
+
resolution: 512 | 1024;
|
|
3711
4905
|
/**
|
|
3712
|
-
*
|
|
3713
|
-
* @description
|
|
4906
|
+
* Training Steps
|
|
4907
|
+
* @description Number of training steps run.
|
|
3714
4908
|
*/
|
|
3715
|
-
|
|
4909
|
+
training_steps: number;
|
|
3716
4910
|
}
|
|
3717
4911
|
|
|
3718
4912
|
export interface LightingDetails {
|
|
@@ -3733,7 +4927,7 @@ export interface LightingDetails {
|
|
|
3733
4927
|
shadows?: string;
|
|
3734
4928
|
}
|
|
3735
4929
|
|
|
3736
|
-
export
|
|
4930
|
+
export interface Lighting_1 {
|
|
3737
4931
|
/**
|
|
3738
4932
|
* Conditions
|
|
3739
4933
|
* @description The conditions of the lighting in the image to be generated.
|
|
@@ -3749,9 +4943,8 @@ export type Lighting_1 = {
|
|
|
3749
4943
|
* @description The shadows in the image to be generated.
|
|
3750
4944
|
*/
|
|
3751
4945
|
shadows?: string;
|
|
3752
|
-
|
|
3753
|
-
|
|
3754
|
-
};
|
|
4946
|
+
[key: string]: any;
|
|
4947
|
+
}
|
|
3755
4948
|
|
|
3756
4949
|
export interface Lighting {
|
|
3757
4950
|
/**
|
|
@@ -3771,24 +4964,6 @@ export interface Lighting {
|
|
|
3771
4964
|
shadows?: string;
|
|
3772
4965
|
}
|
|
3773
4966
|
|
|
3774
|
-
export interface LavaSRTimings {
|
|
3775
|
-
/**
|
|
3776
|
-
* Inference
|
|
3777
|
-
* @description Time taken to run the inference in seconds.
|
|
3778
|
-
*/
|
|
3779
|
-
inference: number;
|
|
3780
|
-
/**
|
|
3781
|
-
* Postprocess
|
|
3782
|
-
* @description Time taken to postprocess the audio in seconds.
|
|
3783
|
-
*/
|
|
3784
|
-
postprocess: number;
|
|
3785
|
-
/**
|
|
3786
|
-
* Preprocess
|
|
3787
|
-
* @description Time taken to preprocess the audio in seconds.
|
|
3788
|
-
*/
|
|
3789
|
-
preprocess: number;
|
|
3790
|
-
}
|
|
3791
|
-
|
|
3792
4967
|
export interface KlingV3MultiPromptElement {
|
|
3793
4968
|
/**
|
|
3794
4969
|
* Duration
|
|
@@ -3850,7 +5025,7 @@ export interface KlingV3ComboElementInput {
|
|
|
3850
5025
|
video_url?: string;
|
|
3851
5026
|
/**
|
|
3852
5027
|
* Voice Id
|
|
3853
|
-
* @description The voice ID for this element. The voice will be binded to the element and references to this element will use the binded voice.
|
|
5028
|
+
* @description The voice ID for this element. The voice will be binded to the element and references to this element will use the binded voice. Get voice IDs from the following endpoint: https://fal.ai/models/fal-ai/kling-video/create-voice
|
|
3854
5029
|
*/
|
|
3855
5030
|
voice_id?: string;
|
|
3856
5031
|
}
|
|
@@ -3870,7 +5045,7 @@ export interface KeyframeTransition {
|
|
|
3870
5045
|
prompt?: string;
|
|
3871
5046
|
}
|
|
3872
5047
|
|
|
3873
|
-
export interface
|
|
5048
|
+
export interface Keyframe_1 {
|
|
3874
5049
|
/**
|
|
3875
5050
|
* Duration
|
|
3876
5051
|
* @description The duration in milliseconds of this keyframe
|
|
@@ -3888,6 +5063,21 @@ export interface Keyframe {
|
|
|
3888
5063
|
url: string;
|
|
3889
5064
|
}
|
|
3890
5065
|
|
|
5066
|
+
export interface Keyframe {
|
|
5067
|
+
/**
|
|
5068
|
+
* Frame Index
|
|
5069
|
+
* @description 0-based output frame index for this keyframe. Must be >= 1 (frame 0 is the restyled first frame from `image_url`) and less than the output frame count.
|
|
5070
|
+
* @example 80
|
|
5071
|
+
*/
|
|
5072
|
+
frame_index: number;
|
|
5073
|
+
/**
|
|
5074
|
+
* Image Url
|
|
5075
|
+
* @description URL of a restyled keyframe image. It is pinned verbatim at `frame_index` to anchor identity over long videos. Its aspect ratio must match the output aspect ratio within 0.1.
|
|
5076
|
+
* @example https://storage.googleapis.com/falserverless/example_inputs/ltxv-image-input.jpg
|
|
5077
|
+
*/
|
|
5078
|
+
image_url: string;
|
|
5079
|
+
}
|
|
5080
|
+
|
|
3891
5081
|
export interface IPAdapter_1 {
|
|
3892
5082
|
/**
|
|
3893
5083
|
* Image Projection Shortcut
|
|
@@ -4002,19 +5192,59 @@ export interface IPAdapter {
|
|
|
4002
5192
|
weight_name?: string;
|
|
4003
5193
|
}
|
|
4004
5194
|
|
|
4005
|
-
export interface
|
|
5195
|
+
export interface InterpolateValidation {
|
|
4006
5196
|
/**
|
|
4007
|
-
* End
|
|
4008
|
-
* @description
|
|
4009
|
-
* @example 9.45
|
|
5197
|
+
* End Image Url
|
|
5198
|
+
* @description URL to the last-frame keyframe image.
|
|
4010
5199
|
*/
|
|
4011
|
-
|
|
5200
|
+
end_image_url: string;
|
|
4012
5201
|
/**
|
|
4013
|
-
*
|
|
4014
|
-
* @description
|
|
4015
|
-
* @example 0
|
|
5202
|
+
* Middle Image Url
|
|
5203
|
+
* @description Optional URL to a middle keyframe image; required when the run sets include_middle_keyframe=true (first+middle+last interpolation).
|
|
4016
5204
|
*/
|
|
4017
|
-
|
|
5205
|
+
middle_image_url?: string;
|
|
5206
|
+
/**
|
|
5207
|
+
* Prompt
|
|
5208
|
+
* @description The prompt to use for validation.
|
|
5209
|
+
*/
|
|
5210
|
+
prompt: string;
|
|
5211
|
+
/**
|
|
5212
|
+
* Start Image Url
|
|
5213
|
+
* @description URL to the first-frame keyframe image.
|
|
5214
|
+
*/
|
|
5215
|
+
start_image_url: string;
|
|
5216
|
+
}
|
|
5217
|
+
|
|
5218
|
+
export interface InpaintValidation {
|
|
5219
|
+
/**
|
|
5220
|
+
* Mask Url
|
|
5221
|
+
* @description URL to the inpainting mask (image or video). Standard convention: WHITE marks the region to regenerate/edit, BLACK is kept unchanged. Resolution need not match the video; it is resized automatically.
|
|
5222
|
+
*/
|
|
5223
|
+
mask_url: string;
|
|
5224
|
+
/**
|
|
5225
|
+
* Prompt
|
|
5226
|
+
* @description The prompt to use for validation.
|
|
5227
|
+
*/
|
|
5228
|
+
prompt: string;
|
|
5229
|
+
/**
|
|
5230
|
+
* Video Url
|
|
5231
|
+
* @description URL to the source video to inpaint.
|
|
5232
|
+
*/
|
|
5233
|
+
video_url: string;
|
|
5234
|
+
}
|
|
5235
|
+
|
|
5236
|
+
export interface ImageStyleReference {
|
|
5237
|
+
/**
|
|
5238
|
+
* Image Url
|
|
5239
|
+
* @description Publicly accessible URL of a reference image.
|
|
5240
|
+
*/
|
|
5241
|
+
image_url: string;
|
|
5242
|
+
/**
|
|
5243
|
+
* Strength
|
|
5244
|
+
* @description How strongly the reference influences the generated image. Negative values push away from the reference.
|
|
5245
|
+
* @default 1
|
|
5246
|
+
*/
|
|
5247
|
+
strength?: number;
|
|
4018
5248
|
}
|
|
4019
5249
|
|
|
4020
5250
|
export interface ImageSize {
|
|
@@ -4076,12 +5306,18 @@ export interface ImagePrompt {
|
|
|
4076
5306
|
weight?: number;
|
|
4077
5307
|
}
|
|
4078
5308
|
|
|
4079
|
-
export interface
|
|
5309
|
+
export interface ImageFrame {
|
|
5310
|
+
/**
|
|
5311
|
+
* Frames
|
|
5312
|
+
* @description Number of frames this image is held for in the output video. The on-screen duration is `frames / fps` seconds.
|
|
5313
|
+
*/
|
|
5314
|
+
frames: number;
|
|
4080
5315
|
/**
|
|
4081
|
-
*
|
|
4082
|
-
* @description
|
|
5316
|
+
* Url
|
|
5317
|
+
* @description URL where the image file can be accessed
|
|
5318
|
+
* @example https://v3.fal.media/files/koala/oei_-iPIYFnhdB8SxojND_qwen-edit-res.png
|
|
4083
5319
|
*/
|
|
4084
|
-
|
|
5320
|
+
url: string;
|
|
4085
5321
|
}
|
|
4086
5322
|
|
|
4087
5323
|
export interface ImageFillInput_1 {
|
|
@@ -4182,78 +5418,73 @@ export interface ImageConditioningInput {
|
|
|
4182
5418
|
strength?: number;
|
|
4183
5419
|
}
|
|
4184
5420
|
|
|
4185
|
-
export interface
|
|
4186
|
-
/**
|
|
4187
|
-
* Image Url
|
|
4188
|
-
* @description The URL of the image to use as input.
|
|
4189
|
-
*/
|
|
4190
|
-
image_url: string;
|
|
4191
|
-
/**
|
|
4192
|
-
* Start Frame Number
|
|
4193
|
-
* @description The frame number to start the condition on.
|
|
4194
|
-
* @default 0
|
|
4195
|
-
*/
|
|
4196
|
-
start_frame_number?: number;
|
|
4197
|
-
/**
|
|
4198
|
-
* Strength
|
|
4199
|
-
* @description The strength of the condition.
|
|
4200
|
-
* @default 1
|
|
4201
|
-
*/
|
|
4202
|
-
strength?: number;
|
|
4203
|
-
}
|
|
4204
|
-
|
|
4205
|
-
export interface Image_3 {
|
|
5421
|
+
export interface Image_2 {
|
|
4206
5422
|
/**
|
|
4207
5423
|
* Content Type
|
|
4208
5424
|
* @description The mime type of the file.
|
|
5425
|
+
* @default null
|
|
4209
5426
|
* @example image/png
|
|
4210
5427
|
*/
|
|
4211
|
-
content_type
|
|
5428
|
+
content_type?: string;
|
|
5429
|
+
/**
|
|
5430
|
+
* File Data
|
|
5431
|
+
* @description File data
|
|
5432
|
+
* @default null
|
|
5433
|
+
*/
|
|
5434
|
+
file_data?: string;
|
|
4212
5435
|
/**
|
|
4213
5436
|
* File Name
|
|
4214
5437
|
* @description The name of the file. It will be auto-generated if not provided.
|
|
5438
|
+
* @default null
|
|
4215
5439
|
* @example z9RV14K95DvU.png
|
|
4216
5440
|
*/
|
|
4217
|
-
file_name
|
|
5441
|
+
file_name?: string;
|
|
4218
5442
|
/**
|
|
4219
5443
|
* File Size
|
|
4220
5444
|
* @description The size of the file in bytes.
|
|
5445
|
+
* @default null
|
|
4221
5446
|
* @example 4404019
|
|
4222
5447
|
*/
|
|
4223
|
-
file_size
|
|
5448
|
+
file_size?: number;
|
|
4224
5449
|
/**
|
|
4225
5450
|
* Height
|
|
4226
5451
|
* @description The height of the image in pixels.
|
|
5452
|
+
* @default null
|
|
4227
5453
|
* @example 1024
|
|
4228
5454
|
*/
|
|
4229
5455
|
height?: number;
|
|
4230
5456
|
/**
|
|
4231
5457
|
* Url
|
|
4232
5458
|
* @description The URL where the file can be downloaded from.
|
|
4233
|
-
* @example https://url.to/generated/file/z9RV14K95DvU.png
|
|
4234
5459
|
*/
|
|
4235
5460
|
url: string;
|
|
4236
5461
|
/**
|
|
4237
5462
|
* Width
|
|
4238
5463
|
* @description The width of the image in pixels.
|
|
5464
|
+
* @default null
|
|
4239
5465
|
* @example 1024
|
|
4240
5466
|
*/
|
|
4241
5467
|
width?: number;
|
|
4242
5468
|
}
|
|
4243
5469
|
|
|
4244
|
-
export interface
|
|
5470
|
+
export interface Image_1 {
|
|
4245
5471
|
/**
|
|
4246
5472
|
* Content Type
|
|
4247
|
-
* @
|
|
4248
|
-
* @example image/png
|
|
5473
|
+
* @default image/jpeg
|
|
4249
5474
|
*/
|
|
4250
5475
|
content_type?: string;
|
|
5476
|
+
height: number;
|
|
5477
|
+
url: string;
|
|
5478
|
+
width: number;
|
|
5479
|
+
}
|
|
5480
|
+
|
|
5481
|
+
export interface Image {
|
|
4251
5482
|
/**
|
|
4252
|
-
*
|
|
4253
|
-
*
|
|
4254
|
-
* @
|
|
5483
|
+
* Content Type
|
|
5484
|
+
* @description The mime type of the file.
|
|
5485
|
+
* @example image/png
|
|
4255
5486
|
*/
|
|
4256
|
-
|
|
5487
|
+
content_type?: string;
|
|
4257
5488
|
/**
|
|
4258
5489
|
* File Name
|
|
4259
5490
|
* @description The name of the file. It will be auto-generated if not provided.
|
|
@@ -4267,95 +5498,335 @@ export interface Image_2 {
|
|
|
4267
5498
|
*/
|
|
4268
5499
|
file_size?: number;
|
|
4269
5500
|
/**
|
|
4270
|
-
* Height
|
|
4271
|
-
* @description The height of the image in pixels.
|
|
4272
|
-
* @example 1024
|
|
5501
|
+
* Height
|
|
5502
|
+
* @description The height of the image in pixels.
|
|
5503
|
+
* @example 1024
|
|
5504
|
+
*/
|
|
5505
|
+
height?: number;
|
|
5506
|
+
/**
|
|
5507
|
+
* Url
|
|
5508
|
+
* @description The URL where the file can be downloaded from.
|
|
5509
|
+
*/
|
|
5510
|
+
url: string;
|
|
5511
|
+
/**
|
|
5512
|
+
* Width
|
|
5513
|
+
* @description The width of the image in pixels.
|
|
5514
|
+
* @example 1024
|
|
5515
|
+
*/
|
|
5516
|
+
width?: number;
|
|
5517
|
+
}
|
|
5518
|
+
|
|
5519
|
+
export interface IceServersOutput {
|
|
5520
|
+
iceservers: {
|
|
5521
|
+
[key: string]: { [x: string]: any } | null;
|
|
5522
|
+
}[];
|
|
5523
|
+
/**
|
|
5524
|
+
* @description discriminator enum property added by openapi-typescript
|
|
5525
|
+
* @enum {string}
|
|
5526
|
+
*/
|
|
5527
|
+
type: 'iceservers';
|
|
5528
|
+
}
|
|
5529
|
+
|
|
5530
|
+
export interface IceCandidateOutput {
|
|
5531
|
+
candidate: IceCandidate;
|
|
5532
|
+
/**
|
|
5533
|
+
* @description discriminator enum property added by openapi-typescript
|
|
5534
|
+
* @enum {string}
|
|
5535
|
+
*/
|
|
5536
|
+
type: 'icecandidate';
|
|
5537
|
+
}
|
|
5538
|
+
|
|
5539
|
+
export interface IceCandidate {
|
|
5540
|
+
candidate: string;
|
|
5541
|
+
/**
|
|
5542
|
+
* Sdpmid
|
|
5543
|
+
* @default null
|
|
5544
|
+
*/
|
|
5545
|
+
sdpMid?: string;
|
|
5546
|
+
/**
|
|
5547
|
+
* Sdpmlineindex
|
|
5548
|
+
* @default null
|
|
5549
|
+
*/
|
|
5550
|
+
sdpMLineIndex?: number;
|
|
5551
|
+
}
|
|
5552
|
+
|
|
5553
|
+
export interface I2VValidation {
|
|
5554
|
+
/**
|
|
5555
|
+
* Image Url
|
|
5556
|
+
* @description An image to use as the first frame for image-to-video validation.
|
|
5557
|
+
*/
|
|
5558
|
+
image_url: string;
|
|
5559
|
+
/**
|
|
5560
|
+
* Prompt
|
|
5561
|
+
* @description The prompt to use for validation.
|
|
5562
|
+
*/
|
|
5563
|
+
prompt: string;
|
|
5564
|
+
}
|
|
5565
|
+
|
|
5566
|
+
export interface H3MaxCameraKeyframe {
|
|
5567
|
+
/**
|
|
5568
|
+
* Azimuth
|
|
5569
|
+
* @description Horizontal camera angle around the subject, in degrees.
|
|
5570
|
+
*/
|
|
5571
|
+
azimuth: number;
|
|
5572
|
+
/**
|
|
5573
|
+
* Distance
|
|
5574
|
+
* @description Camera distance from the subject in normalized scene units.
|
|
5575
|
+
*/
|
|
5576
|
+
distance: number;
|
|
5577
|
+
/**
|
|
5578
|
+
* Elevation
|
|
5579
|
+
* @description Vertical camera angle around the subject, in degrees.
|
|
5580
|
+
*/
|
|
5581
|
+
elevation: number;
|
|
5582
|
+
/**
|
|
5583
|
+
* Time
|
|
5584
|
+
* @description Normalized video time, from 0 at the start to 1 at the end.
|
|
5585
|
+
*/
|
|
5586
|
+
time: number;
|
|
5587
|
+
}
|
|
5588
|
+
|
|
5589
|
+
export interface GuidanceInput {
|
|
5590
|
+
/**
|
|
5591
|
+
* Image Url
|
|
5592
|
+
* @description The image that should be used as guidance, in base64 format, with the method defined in guidance_method_1. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB. If more then one guidance method is used, all guidance images must be of the same aspect ratio, and this will be the aspect ratio of the generated results. If guidance_method_1 is selected, an image must be provided.
|
|
5593
|
+
*/
|
|
5594
|
+
image_url: string;
|
|
5595
|
+
/**
|
|
5596
|
+
* Method
|
|
5597
|
+
* @description Which guidance type you would like to include in the generation. Up to 4 guidance methods can be combined during a single inference. This parameter is optional.
|
|
5598
|
+
* @enum {string}
|
|
5599
|
+
*/
|
|
5600
|
+
method?:
|
|
5601
|
+
| 'controlnet_canny'
|
|
5602
|
+
| 'controlnet_depth'
|
|
5603
|
+
| 'controlnet_recoloring'
|
|
5604
|
+
| 'controlnet_color_grid';
|
|
5605
|
+
/**
|
|
5606
|
+
* Scale
|
|
5607
|
+
* @description Impact of the guidance.
|
|
5608
|
+
* @default 1
|
|
5609
|
+
*/
|
|
5610
|
+
scale?: number;
|
|
5611
|
+
}
|
|
5612
|
+
|
|
5613
|
+
export interface GrokXSearchTool {
|
|
5614
|
+
/**
|
|
5615
|
+
* Allowed X Handles
|
|
5616
|
+
* @description Restrict results to posts from at most 20 X handles.
|
|
5617
|
+
* @default null
|
|
5618
|
+
*/
|
|
5619
|
+
allowed_x_handles?: string[];
|
|
5620
|
+
/**
|
|
5621
|
+
* Enable Image Understanding
|
|
5622
|
+
* @description Allow the agent to inspect images found on X.
|
|
5623
|
+
* @default null
|
|
5624
|
+
*/
|
|
5625
|
+
enable_image_understanding?: boolean;
|
|
5626
|
+
/**
|
|
5627
|
+
* Enable Video Understanding
|
|
5628
|
+
* @description Allow the agent to inspect videos found on X.
|
|
5629
|
+
* @default null
|
|
5630
|
+
*/
|
|
5631
|
+
enable_video_understanding?: boolean;
|
|
5632
|
+
/**
|
|
5633
|
+
* Enabled
|
|
5634
|
+
* @description Whether to include x_search in session.tools. Disabled by default; set true to let the agent search X posts.
|
|
5635
|
+
* @default false
|
|
5636
|
+
*/
|
|
5637
|
+
enabled?: boolean;
|
|
5638
|
+
/**
|
|
5639
|
+
* Excluded X Handles
|
|
5640
|
+
* @description Exclude posts from at most 20 X handles.
|
|
5641
|
+
* @default null
|
|
5642
|
+
*/
|
|
5643
|
+
excluded_x_handles?: string[];
|
|
5644
|
+
/**
|
|
5645
|
+
* From Date
|
|
5646
|
+
* @description Earliest post date, as ISO YYYY-MM-DD.
|
|
5647
|
+
* @default null
|
|
5648
|
+
*/
|
|
5649
|
+
from_date?: string;
|
|
5650
|
+
/**
|
|
5651
|
+
* To Date
|
|
5652
|
+
* @description Latest post date, as ISO YYYY-MM-DD.
|
|
5653
|
+
* @default null
|
|
5654
|
+
*/
|
|
5655
|
+
to_date?: string;
|
|
5656
|
+
}
|
|
5657
|
+
|
|
5658
|
+
export interface GrokWebSearchTool {
|
|
5659
|
+
/**
|
|
5660
|
+
* Allowed Domains
|
|
5661
|
+
* @description Restrict results to at most five domains, without protocol or path.
|
|
5662
|
+
* @default null
|
|
5663
|
+
*/
|
|
5664
|
+
allowed_domains?: string[];
|
|
5665
|
+
/**
|
|
5666
|
+
* Enable Image Understanding
|
|
5667
|
+
* @description Allow the agent to inspect images found during web search.
|
|
5668
|
+
* @default null
|
|
5669
|
+
*/
|
|
5670
|
+
enable_image_understanding?: boolean;
|
|
5671
|
+
/**
|
|
5672
|
+
* Enabled
|
|
5673
|
+
* @description Whether to include web_search in session.tools. Disabled by default; set true to let the agent search the web.
|
|
5674
|
+
* @default false
|
|
5675
|
+
*/
|
|
5676
|
+
enabled?: boolean;
|
|
5677
|
+
/**
|
|
5678
|
+
* Excluded Domains
|
|
5679
|
+
* @description Exclude results from at most five domains, without protocol or path.
|
|
5680
|
+
* @default null
|
|
5681
|
+
*/
|
|
5682
|
+
excluded_domains?: string[];
|
|
5683
|
+
/**
|
|
5684
|
+
* @description Optional location used to localize search results.
|
|
5685
|
+
* @default null
|
|
5686
|
+
*/
|
|
5687
|
+
location?: GrokSearchLocation;
|
|
5688
|
+
}
|
|
5689
|
+
|
|
5690
|
+
export interface GrokTurnDetectionConfiguration {
|
|
5691
|
+
/**
|
|
5692
|
+
* Idle Timeout (ms)
|
|
5693
|
+
* @description Idle time after an assistant response before xAI starts a proactive turn, in milliseconds.
|
|
5694
|
+
* @default null
|
|
5695
|
+
*/
|
|
5696
|
+
idle_timeout_ms?: number;
|
|
5697
|
+
/**
|
|
5698
|
+
* Prefix Padding (ms)
|
|
5699
|
+
* @description Audio retained before detected speech, in milliseconds.
|
|
5700
|
+
* @default null
|
|
5701
|
+
*/
|
|
5702
|
+
prefix_padding_ms?: number;
|
|
5703
|
+
/**
|
|
5704
|
+
* Silence Duration (ms)
|
|
5705
|
+
* @description Silence duration that ends a detected turn, in milliseconds.
|
|
5706
|
+
* @default null
|
|
5707
|
+
*/
|
|
5708
|
+
silence_duration_ms?: number;
|
|
5709
|
+
/**
|
|
5710
|
+
* Threshold
|
|
5711
|
+
* @description VAD activation threshold; higher values require louder audio.
|
|
5712
|
+
* @default null
|
|
5713
|
+
*/
|
|
5714
|
+
threshold?: number;
|
|
5715
|
+
}
|
|
5716
|
+
|
|
5717
|
+
export interface GrokToolsConfiguration {
|
|
5718
|
+
/**
|
|
5719
|
+
* MCP Servers
|
|
5720
|
+
* @description Remote MCP servers that xAI connects to and executes.
|
|
5721
|
+
*/
|
|
5722
|
+
mcp_servers?: GrokRemoteMCPTool[];
|
|
5723
|
+
/**
|
|
5724
|
+
* @description xAI-managed web search; off unless enabled is set true.
|
|
5725
|
+
* @default {
|
|
5726
|
+
* "enabled": false,
|
|
5727
|
+
* "excluded_domains": null,
|
|
5728
|
+
* "enable_image_understanding": null,
|
|
5729
|
+
* "allowed_domains": null,
|
|
5730
|
+
* "location": null
|
|
5731
|
+
* }
|
|
5732
|
+
*/
|
|
5733
|
+
web_search?: GrokWebSearchTool;
|
|
5734
|
+
/**
|
|
5735
|
+
* @description xAI-managed X search; off unless enabled is set true.
|
|
5736
|
+
* @default {
|
|
5737
|
+
* "enabled": false,
|
|
5738
|
+
* "enable_video_understanding": null,
|
|
5739
|
+
* "from_date": null,
|
|
5740
|
+
* "enable_image_understanding": null,
|
|
5741
|
+
* "to_date": null,
|
|
5742
|
+
* "excluded_x_handles": null,
|
|
5743
|
+
* "allowed_x_handles": null
|
|
5744
|
+
* }
|
|
5745
|
+
*/
|
|
5746
|
+
x_search?: GrokXSearchTool;
|
|
5747
|
+
}
|
|
5748
|
+
|
|
5749
|
+
export interface GrokSearchLocation {
|
|
5750
|
+
/**
|
|
5751
|
+
* City
|
|
5752
|
+
* @description City used to localize web-search results.
|
|
5753
|
+
* @default null
|
|
5754
|
+
*/
|
|
5755
|
+
city?: string;
|
|
5756
|
+
/**
|
|
5757
|
+
* Country
|
|
5758
|
+
* @description Country used to localize web-search results.
|
|
5759
|
+
* @default null
|
|
4273
5760
|
*/
|
|
4274
|
-
|
|
5761
|
+
country?: string;
|
|
4275
5762
|
/**
|
|
4276
|
-
*
|
|
4277
|
-
* @description
|
|
5763
|
+
* Region
|
|
5764
|
+
* @description Region used to localize web-search results.
|
|
5765
|
+
* @default null
|
|
4278
5766
|
*/
|
|
4279
|
-
|
|
5767
|
+
region?: string;
|
|
4280
5768
|
/**
|
|
4281
|
-
*
|
|
4282
|
-
* @description
|
|
4283
|
-
* @
|
|
5769
|
+
* Timezone
|
|
5770
|
+
* @description IANA timezone name, for example America/New_York.
|
|
5771
|
+
* @default null
|
|
4284
5772
|
*/
|
|
4285
|
-
|
|
5773
|
+
timezone?: string;
|
|
4286
5774
|
}
|
|
4287
5775
|
|
|
4288
|
-
export interface
|
|
5776
|
+
export interface GrokRemoteMCPTool {
|
|
4289
5777
|
/**
|
|
4290
|
-
*
|
|
4291
|
-
* @
|
|
5778
|
+
* Allowed Tools
|
|
5779
|
+
* @description Optional allow-list of tool names exposed from this server.
|
|
5780
|
+
* @default null
|
|
4292
5781
|
*/
|
|
4293
|
-
|
|
4294
|
-
height: number;
|
|
4295
|
-
url: string;
|
|
4296
|
-
width: number;
|
|
4297
|
-
}
|
|
4298
|
-
|
|
4299
|
-
export interface Image {
|
|
5782
|
+
allowed_tools?: string[];
|
|
4300
5783
|
/**
|
|
4301
|
-
*
|
|
4302
|
-
* @description
|
|
4303
|
-
* @
|
|
5784
|
+
* Authorization
|
|
5785
|
+
* @description Sensitive authorization value forwarded only to xAI.
|
|
5786
|
+
* @default null
|
|
4304
5787
|
*/
|
|
4305
|
-
|
|
5788
|
+
authorization?: string;
|
|
4306
5789
|
/**
|
|
4307
|
-
*
|
|
4308
|
-
* @description
|
|
4309
|
-
* @
|
|
5790
|
+
* Enabled
|
|
5791
|
+
* @description False omits this server.
|
|
5792
|
+
* @default true
|
|
4310
5793
|
*/
|
|
4311
|
-
|
|
5794
|
+
enabled?: boolean;
|
|
4312
5795
|
/**
|
|
4313
|
-
*
|
|
4314
|
-
* @description
|
|
4315
|
-
* @
|
|
5796
|
+
* Headers
|
|
5797
|
+
* @description Sensitive MCP request headers forwarded only to xAI.
|
|
5798
|
+
* @default null
|
|
4316
5799
|
*/
|
|
4317
|
-
|
|
5800
|
+
headers?: {
|
|
5801
|
+
[key: string]: string;
|
|
5802
|
+
};
|
|
4318
5803
|
/**
|
|
4319
|
-
*
|
|
4320
|
-
* @description
|
|
4321
|
-
* @
|
|
5804
|
+
* Server Description
|
|
5805
|
+
* @description Description of the capabilities exposed by this server.
|
|
5806
|
+
* @default null
|
|
4322
5807
|
*/
|
|
4323
|
-
|
|
5808
|
+
server_description?: string;
|
|
4324
5809
|
/**
|
|
4325
|
-
*
|
|
4326
|
-
* @description
|
|
5810
|
+
* Server Label
|
|
5811
|
+
* @description Label xAI uses to identify and prefix this server's tools.
|
|
4327
5812
|
*/
|
|
4328
|
-
|
|
5813
|
+
server_label: string;
|
|
4329
5814
|
/**
|
|
4330
|
-
*
|
|
4331
|
-
*
|
|
4332
|
-
* @
|
|
5815
|
+
* Server Url
|
|
5816
|
+
* Format: uri
|
|
5817
|
+
* @description Caller-selected HTTP(S) MCP endpoint. xAI makes the remote connection and supports Streaming HTTP/SSE transports. Use at your own risk; fal does not connect to or SSRF-fetch this URL.
|
|
4333
5818
|
*/
|
|
4334
|
-
|
|
5819
|
+
server_url: string;
|
|
4335
5820
|
}
|
|
4336
5821
|
|
|
4337
|
-
export interface
|
|
5822
|
+
export interface GenerativeShadow {
|
|
5823
|
+
light_source?: ShadowLightSource;
|
|
4338
5824
|
/**
|
|
4339
|
-
*
|
|
4340
|
-
* @description
|
|
4341
|
-
|
|
4342
|
-
image_url: string;
|
|
4343
|
-
/**
|
|
4344
|
-
* Method
|
|
4345
|
-
* @description Which guidance type you would like to include in the generation. Up to 4 guidance methods can be combined during a single inference. This parameter is optional.
|
|
4346
|
-
* @enum {string}
|
|
4347
|
-
*/
|
|
4348
|
-
method?:
|
|
4349
|
-
| 'controlnet_canny'
|
|
4350
|
-
| 'controlnet_depth'
|
|
4351
|
-
| 'controlnet_recoloring'
|
|
4352
|
-
| 'controlnet_color_grid';
|
|
4353
|
-
/**
|
|
4354
|
-
* Scale
|
|
4355
|
-
* @description Impact of the guidance.
|
|
4356
|
-
* @default 1
|
|
5825
|
+
* Opacity
|
|
5826
|
+
* @description Final composited shadow opacity (0–1).
|
|
5827
|
+
* @default 0.2
|
|
4357
5828
|
*/
|
|
4358
|
-
|
|
5829
|
+
opacity?: number;
|
|
4359
5830
|
}
|
|
4360
5831
|
|
|
4361
5832
|
export interface Frame {
|
|
@@ -4366,61 +5837,85 @@ export interface Frame {
|
|
|
4366
5837
|
url: string;
|
|
4367
5838
|
}
|
|
4368
5839
|
|
|
4369
|
-
export interface
|
|
5840
|
+
export interface ForcedAlignmentWord {
|
|
4370
5841
|
/**
|
|
4371
|
-
*
|
|
4372
|
-
* @description
|
|
4373
|
-
* @example 0
|
|
5842
|
+
* End
|
|
5843
|
+
* @description End time in seconds
|
|
4374
5844
|
*/
|
|
4375
|
-
|
|
5845
|
+
end: number;
|
|
4376
5846
|
/**
|
|
4377
|
-
*
|
|
4378
|
-
* @description
|
|
4379
|
-
* @example 350
|
|
5847
|
+
* Loss
|
|
5848
|
+
* @description Average alignment loss for the word
|
|
4380
5849
|
*/
|
|
4381
|
-
|
|
5850
|
+
loss: number;
|
|
4382
5851
|
/**
|
|
4383
|
-
*
|
|
4384
|
-
* @description
|
|
4385
|
-
* @default -1
|
|
5852
|
+
* Start
|
|
5853
|
+
* @description Start time in seconds
|
|
4386
5854
|
*/
|
|
4387
|
-
|
|
5855
|
+
start: number;
|
|
4388
5856
|
/**
|
|
4389
|
-
*
|
|
4390
|
-
* @description
|
|
4391
|
-
* @example 0.22
|
|
5857
|
+
* Text
|
|
5858
|
+
* @description The aligned character
|
|
4392
5859
|
*/
|
|
4393
|
-
|
|
5860
|
+
text: string;
|
|
5861
|
+
}
|
|
5862
|
+
|
|
5863
|
+
export interface ForcedAlignmentCharacter {
|
|
4394
5864
|
/**
|
|
4395
|
-
*
|
|
4396
|
-
* @description
|
|
4397
|
-
* @example 0.18
|
|
5865
|
+
* End
|
|
5866
|
+
* @description End time in seconds
|
|
4398
5867
|
*/
|
|
4399
|
-
|
|
5868
|
+
end: number;
|
|
5869
|
+
/**
|
|
5870
|
+
* Start
|
|
5871
|
+
* @description Start time in seconds
|
|
5872
|
+
*/
|
|
5873
|
+
start: number;
|
|
5874
|
+
/**
|
|
5875
|
+
* Text
|
|
5876
|
+
* @description The aligned character
|
|
5877
|
+
*/
|
|
5878
|
+
text: string;
|
|
5879
|
+
}
|
|
5880
|
+
|
|
5881
|
+
export interface Flux3Keyframe {
|
|
5882
|
+
/**
|
|
5883
|
+
* Frame Index
|
|
5884
|
+
* @description Frame position of this keyframe in the generated 24 fps video. Must be unique and at most `duration * 24`.
|
|
5885
|
+
*/
|
|
5886
|
+
frame_index: number;
|
|
5887
|
+
/**
|
|
5888
|
+
* Image URL
|
|
5889
|
+
* @description URL of the keyframe image (PNG, JPEG, or WebP).
|
|
5890
|
+
*/
|
|
5891
|
+
image_url: string;
|
|
4400
5892
|
}
|
|
4401
5893
|
|
|
4402
5894
|
export interface File_1 {
|
|
4403
5895
|
/**
|
|
4404
5896
|
* Content Type
|
|
4405
5897
|
* @description The mime type of the file.
|
|
5898
|
+
* @default null
|
|
4406
5899
|
* @example image/png
|
|
4407
5900
|
*/
|
|
4408
5901
|
content_type?: string;
|
|
4409
5902
|
/**
|
|
4410
5903
|
* File Data
|
|
4411
|
-
* Format: binary
|
|
4412
5904
|
* @description File data
|
|
5905
|
+
* @default null
|
|
4413
5906
|
*/
|
|
4414
5907
|
file_data?: string;
|
|
4415
5908
|
/**
|
|
4416
5909
|
* File Name
|
|
4417
5910
|
* @description The name of the file. It will be auto-generated if not provided.
|
|
5911
|
+
* @default null
|
|
4418
5912
|
* @example z9RV14K95DvU.png
|
|
4419
5913
|
*/
|
|
4420
5914
|
file_name?: string;
|
|
4421
5915
|
/**
|
|
4422
5916
|
* File Size
|
|
4423
5917
|
* @description The size of the file in bytes.
|
|
5918
|
+
* @default null
|
|
4424
5919
|
* @example 4404019
|
|
4425
5920
|
*/
|
|
4426
5921
|
file_size?: number;
|
|
@@ -4509,6 +6004,63 @@ export interface ExtendVideoConditioningInput {
|
|
|
4509
6004
|
video_url: string;
|
|
4510
6005
|
}
|
|
4511
6006
|
|
|
6007
|
+
export interface ExtendValidation {
|
|
6008
|
+
/**
|
|
6009
|
+
* Prompt
|
|
6010
|
+
* @description The prompt to use for validation.
|
|
6011
|
+
*/
|
|
6012
|
+
prompt: string;
|
|
6013
|
+
/**
|
|
6014
|
+
* Video Url
|
|
6015
|
+
* @description URL to the video the model should temporally extend.
|
|
6016
|
+
*/
|
|
6017
|
+
video_url: string;
|
|
6018
|
+
}
|
|
6019
|
+
|
|
6020
|
+
export interface EventSegment_1 {
|
|
6021
|
+
/**
|
|
6022
|
+
* End
|
|
6023
|
+
* @description End time in seconds.
|
|
6024
|
+
* @example 12.5
|
|
6025
|
+
*/
|
|
6026
|
+
end: number;
|
|
6027
|
+
/**
|
|
6028
|
+
* Start
|
|
6029
|
+
* @description Start time in seconds.
|
|
6030
|
+
* @example 10.4
|
|
6031
|
+
*/
|
|
6032
|
+
start: number;
|
|
6033
|
+
}
|
|
6034
|
+
|
|
6035
|
+
export interface EventSegment {
|
|
6036
|
+
/**
|
|
6037
|
+
* End
|
|
6038
|
+
* @description End time in seconds.
|
|
6039
|
+
* @example 12.5
|
|
6040
|
+
*/
|
|
6041
|
+
end: number;
|
|
6042
|
+
/**
|
|
6043
|
+
* Start
|
|
6044
|
+
* @description Start time in seconds.
|
|
6045
|
+
* @example 10.4
|
|
6046
|
+
*/
|
|
6047
|
+
start: number;
|
|
6048
|
+
/**
|
|
6049
|
+
* Text
|
|
6050
|
+
* @description Short description of the event (caption mode only).
|
|
6051
|
+
*/
|
|
6052
|
+
text?: string;
|
|
6053
|
+
}
|
|
6054
|
+
|
|
6055
|
+
export interface ErrorOutput {
|
|
6056
|
+
error: string;
|
|
6057
|
+
/**
|
|
6058
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6059
|
+
* @enum {string}
|
|
6060
|
+
*/
|
|
6061
|
+
type: 'error';
|
|
6062
|
+
}
|
|
6063
|
+
|
|
4512
6064
|
export interface EmotionalStrengths {
|
|
4513
6065
|
/**
|
|
4514
6066
|
* Afraid
|
|
@@ -4566,7 +6118,7 @@ export interface EmbedItem {
|
|
|
4566
6118
|
* Image Source
|
|
4567
6119
|
* @description URL of the image.
|
|
4568
6120
|
*/
|
|
4569
|
-
image_source
|
|
6121
|
+
image_source: string;
|
|
4570
6122
|
}
|
|
4571
6123
|
|
|
4572
6124
|
export interface Embedding_1 {
|
|
@@ -4577,11 +6129,9 @@ export interface Embedding_1 {
|
|
|
4577
6129
|
path: string;
|
|
4578
6130
|
/**
|
|
4579
6131
|
* Tokens
|
|
4580
|
-
* @description The tokens to map the embedding weights to. Use these tokens in your
|
|
4581
|
-
*
|
|
4582
|
-
*
|
|
4583
|
-
* "<s1>"
|
|
4584
|
-
* ]
|
|
6132
|
+
* @description The tokens to map the embedding weights to. Use these tokens in your
|
|
6133
|
+
* prompts. When omitted, tokens are generated as <s0>, <s1>, ... to
|
|
6134
|
+
* match the number of vectors in the embedding file.
|
|
4585
6135
|
*/
|
|
4586
6136
|
tokens?: string[];
|
|
4587
6137
|
}
|
|
@@ -4596,11 +6146,10 @@ export interface Embedding {
|
|
|
4596
6146
|
path: string;
|
|
4597
6147
|
/**
|
|
4598
6148
|
* Tokens
|
|
4599
|
-
* @description The list of tokens to use for the embedding.
|
|
4600
|
-
*
|
|
4601
|
-
*
|
|
4602
|
-
*
|
|
4603
|
-
* ]
|
|
6149
|
+
* @description The list of tokens to use for the embedding. When omitted, tokens
|
|
6150
|
+
* are generated as <s0>, <s1>, ... to match the number of vectors in
|
|
6151
|
+
* the embedding file.
|
|
6152
|
+
* @default null
|
|
4604
6153
|
*/
|
|
4605
6154
|
tokens?: string[];
|
|
4606
6155
|
}
|
|
@@ -4618,6 +6167,29 @@ export interface ElementInput {
|
|
|
4618
6167
|
reference_image_urls?: string[];
|
|
4619
6168
|
}
|
|
4620
6169
|
|
|
6170
|
+
export interface EditBoundingBox {
|
|
6171
|
+
box?: Box;
|
|
6172
|
+
/**
|
|
6173
|
+
* Description
|
|
6174
|
+
* @description What to draw in this box: the object and its look.
|
|
6175
|
+
* @example a large fluffy knitted dragon in terracotta and mustard yarn
|
|
6176
|
+
*/
|
|
6177
|
+
description: string;
|
|
6178
|
+
/**
|
|
6179
|
+
* Label
|
|
6180
|
+
* @description Short name for the object in this box, e.g. `dragon`. Write `<dragon>` in the prompt to tie the box to those words; a box the prompt doesn't name is added to the scene. Defaults to `obj_<n>`.
|
|
6181
|
+
* @example dragon
|
|
6182
|
+
*/
|
|
6183
|
+
label?: string;
|
|
6184
|
+
source_box?: Box;
|
|
6185
|
+
/**
|
|
6186
|
+
* Source Image Index
|
|
6187
|
+
* @description 0-based index into `image_urls` of the reference the object comes from. Leave unset for a new object.
|
|
6188
|
+
*/
|
|
6189
|
+
source_image_index?: number;
|
|
6190
|
+
target_box?: Box;
|
|
6191
|
+
}
|
|
6192
|
+
|
|
4621
6193
|
export interface EasyControlWeight {
|
|
4622
6194
|
/**
|
|
4623
6195
|
* Control Method Url
|
|
@@ -4651,92 +6223,230 @@ export interface EasyControlWeight {
|
|
|
4651
6223
|
scale?: number;
|
|
4652
6224
|
}
|
|
4653
6225
|
|
|
4654
|
-
export interface
|
|
6226
|
+
export interface DropShadow {
|
|
4655
6227
|
/**
|
|
4656
|
-
*
|
|
4657
|
-
* @description
|
|
4658
|
-
* @
|
|
6228
|
+
* Blur
|
|
6229
|
+
* @description Shadow blur strength (0 to 100). 0 is a hard-edged shadow; 100 is the softest, a radius of 5% of the smaller canvas dimension.
|
|
6230
|
+
* @default 24
|
|
4659
6231
|
*/
|
|
4660
|
-
|
|
6232
|
+
blur?: number;
|
|
6233
|
+
/**
|
|
6234
|
+
* @description Shadow color (R/G/B). Defaults to black.
|
|
6235
|
+
* @default {
|
|
6236
|
+
* "g": 0,
|
|
6237
|
+
* "r": 0,
|
|
6238
|
+
* "b": 0
|
|
6239
|
+
* }
|
|
6240
|
+
*/
|
|
6241
|
+
color?: RGBColor;
|
|
6242
|
+
/**
|
|
6243
|
+
* Horizontal
|
|
6244
|
+
* @description Horizontal shadow offset strength (-100 to 100). Positive moves the shadow right, negative moves it left. 100 is the maximum offset, 10% of the canvas width.
|
|
6245
|
+
* @default 50
|
|
6246
|
+
*/
|
|
6247
|
+
horizontal?: number;
|
|
6248
|
+
/**
|
|
6249
|
+
* Opacity
|
|
6250
|
+
* @description Shadow opacity (0–1).
|
|
6251
|
+
* @default 0.25
|
|
6252
|
+
*/
|
|
6253
|
+
opacity?: number;
|
|
6254
|
+
/**
|
|
6255
|
+
* Vertical
|
|
6256
|
+
* @description Vertical shadow offset strength (-100 to 100). Positive moves the shadow down, negative moves it up. 100 is the maximum offset, 10% of the canvas height.
|
|
6257
|
+
* @default 8
|
|
6258
|
+
*/
|
|
6259
|
+
vertical?: number;
|
|
6260
|
+
}
|
|
6261
|
+
|
|
6262
|
+
export interface DimensionEntry {
|
|
6263
|
+
/**
|
|
6264
|
+
* Name
|
|
6265
|
+
* @description Dimension to render. length/depth are intentionally disabled.
|
|
6266
|
+
* @enum {string}
|
|
6267
|
+
*/
|
|
6268
|
+
name: 'height' | 'width_bottom' | 'width_top';
|
|
6269
|
+
/**
|
|
6270
|
+
* Position
|
|
6271
|
+
* @description Callout side; defaults by dimension name when omitted.
|
|
6272
|
+
*/
|
|
6273
|
+
position?: 'top' | 'bottom' | 'left' | 'right';
|
|
6274
|
+
/**
|
|
6275
|
+
* Unit
|
|
6276
|
+
* @description Physical measurement unit.
|
|
6277
|
+
* @enum {string}
|
|
6278
|
+
*/
|
|
6279
|
+
unit: 'mm' | 'cm' | 'm' | 'in' | '"' | 'ft' | "'";
|
|
6280
|
+
/**
|
|
6281
|
+
* Value
|
|
6282
|
+
* @description Physical measurement value.
|
|
6283
|
+
*/
|
|
6284
|
+
value: number;
|
|
6285
|
+
}
|
|
6286
|
+
|
|
6287
|
+
export interface DialogueBlock {
|
|
6288
|
+
/**
|
|
6289
|
+
* Text
|
|
6290
|
+
* @description The dialogue text
|
|
6291
|
+
*/
|
|
6292
|
+
text: string;
|
|
6293
|
+
/**
|
|
6294
|
+
* Voice
|
|
6295
|
+
* @description The name or the ID of the voice to be used for the generation.
|
|
6296
|
+
* @example Aria
|
|
6297
|
+
* @example Roger
|
|
6298
|
+
* @example Sarah
|
|
6299
|
+
* @example Laura
|
|
6300
|
+
* @example Charlie
|
|
6301
|
+
* @example George
|
|
6302
|
+
* @example Callum
|
|
6303
|
+
* @example River
|
|
6304
|
+
* @example Liam
|
|
6305
|
+
* @example Charlotte
|
|
6306
|
+
* @example Alice
|
|
6307
|
+
* @example Matilda
|
|
6308
|
+
* @example Will
|
|
6309
|
+
* @example Jessica
|
|
6310
|
+
* @example Eric
|
|
6311
|
+
* @example Chris
|
|
6312
|
+
* @example Brian
|
|
6313
|
+
* @example Daniel
|
|
6314
|
+
* @example Lily
|
|
6315
|
+
* @example Bill
|
|
6316
|
+
*/
|
|
6317
|
+
voice: string;
|
|
6318
|
+
}
|
|
6319
|
+
|
|
6320
|
+
export interface DeepFilterNetTimings {
|
|
6321
|
+
/**
|
|
6322
|
+
* Inference
|
|
6323
|
+
* @description Inference time.
|
|
6324
|
+
*/
|
|
6325
|
+
inference: number;
|
|
6326
|
+
/**
|
|
6327
|
+
* Postprocess
|
|
6328
|
+
* @description Postprocessing time.
|
|
6329
|
+
*/
|
|
6330
|
+
postprocess: number;
|
|
6331
|
+
/**
|
|
6332
|
+
* Preprocess
|
|
6333
|
+
* @description Preprocessing time.
|
|
6334
|
+
*/
|
|
6335
|
+
preprocess: number;
|
|
6336
|
+
}
|
|
6337
|
+
|
|
6338
|
+
export interface DecisionsUsage {
|
|
6339
|
+
cost?: number;
|
|
6340
|
+
input_tokens: number;
|
|
6341
|
+
output_tokens: number;
|
|
6342
|
+
total_tokens?: number;
|
|
6343
|
+
}
|
|
6344
|
+
|
|
6345
|
+
export interface DecisionsScoreQuestion {
|
|
6346
|
+
/**
|
|
6347
|
+
* Criteria
|
|
6348
|
+
* @description Ordered level descriptions, from the low end to the high end.
|
|
6349
|
+
*/
|
|
6350
|
+
criteria: (string | Record<string, never> | unknown[])[];
|
|
6351
|
+
/**
|
|
6352
|
+
* Instructions
|
|
6353
|
+
* @description The property to score, as text or structured multimodal content.
|
|
6354
|
+
*/
|
|
6355
|
+
instructions: string | Record<string, never> | { [x: string]: any }[];
|
|
6356
|
+
/**
|
|
6357
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6358
|
+
* @enum {string}
|
|
6359
|
+
*/
|
|
6360
|
+
type: 'score';
|
|
6361
|
+
}
|
|
6362
|
+
|
|
6363
|
+
export interface DecisionsScoreAnswer {
|
|
6364
|
+
confidence?: number;
|
|
6365
|
+
legend?: {
|
|
6366
|
+
[key: string]: string | Record<string, never> | { [x: string]: any }[];
|
|
6367
|
+
};
|
|
6368
|
+
probabilities?: {
|
|
6369
|
+
[key: string]: number;
|
|
6370
|
+
};
|
|
6371
|
+
score: number;
|
|
6372
|
+
/**
|
|
6373
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6374
|
+
* @enum {string}
|
|
6375
|
+
*/
|
|
6376
|
+
type: 'score';
|
|
6377
|
+
}
|
|
6378
|
+
|
|
6379
|
+
export interface DecisionsNoulQuestion {
|
|
6380
|
+
criteria?: DecisionsNoulCriteria;
|
|
6381
|
+
/**
|
|
6382
|
+
* Instructions
|
|
6383
|
+
* @description The yes/no question, as text or structured multimodal content.
|
|
6384
|
+
*/
|
|
6385
|
+
instructions: string | Record<string, never> | { [x: string]: any }[];
|
|
4661
6386
|
/**
|
|
4662
|
-
*
|
|
4663
|
-
* @
|
|
4664
|
-
* @example [
|
|
4665
|
-
* {
|
|
4666
|
-
* "x": 279,
|
|
4667
|
-
* "y": 219
|
|
4668
|
-
* },
|
|
4669
|
-
* {
|
|
4670
|
-
* "x": 417,
|
|
4671
|
-
* "y": 65
|
|
4672
|
-
* }
|
|
4673
|
-
* ]
|
|
6387
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6388
|
+
* @enum {string}
|
|
4674
6389
|
*/
|
|
4675
|
-
|
|
6390
|
+
type: 'noul';
|
|
4676
6391
|
}
|
|
4677
6392
|
|
|
4678
|
-
export interface
|
|
6393
|
+
export interface DecisionsNoulCriteria {
|
|
4679
6394
|
/**
|
|
4680
|
-
*
|
|
4681
|
-
* @description
|
|
6395
|
+
* False
|
|
6396
|
+
* @description What should count as a no/false outcome.
|
|
4682
6397
|
*/
|
|
4683
|
-
|
|
6398
|
+
false: string | Record<string, never> | { [x: string]: any }[];
|
|
4684
6399
|
/**
|
|
4685
|
-
*
|
|
4686
|
-
* @description
|
|
6400
|
+
* True
|
|
6401
|
+
* @description What should count as a yes/true outcome.
|
|
4687
6402
|
*/
|
|
4688
|
-
|
|
6403
|
+
true: string | Record<string, never> | { [x: string]: any }[];
|
|
4689
6404
|
}
|
|
4690
6405
|
|
|
4691
|
-
export interface
|
|
6406
|
+
export interface DecisionsNoulAnswer {
|
|
4692
6407
|
/**
|
|
4693
|
-
*
|
|
4694
|
-
* @description
|
|
6408
|
+
* Noul
|
|
6409
|
+
* @description Probability from 0 to 1 that the answer is yes.
|
|
4695
6410
|
*/
|
|
4696
|
-
|
|
6411
|
+
noul: number;
|
|
4697
6412
|
/**
|
|
4698
|
-
*
|
|
4699
|
-
* @
|
|
4700
|
-
* @example Aria
|
|
4701
|
-
* @example Roger
|
|
4702
|
-
* @example Sarah
|
|
4703
|
-
* @example Laura
|
|
4704
|
-
* @example Charlie
|
|
4705
|
-
* @example George
|
|
4706
|
-
* @example Callum
|
|
4707
|
-
* @example River
|
|
4708
|
-
* @example Liam
|
|
4709
|
-
* @example Charlotte
|
|
4710
|
-
* @example Alice
|
|
4711
|
-
* @example Matilda
|
|
4712
|
-
* @example Will
|
|
4713
|
-
* @example Jessica
|
|
4714
|
-
* @example Eric
|
|
4715
|
-
* @example Chris
|
|
4716
|
-
* @example Brian
|
|
4717
|
-
* @example Daniel
|
|
4718
|
-
* @example Lily
|
|
4719
|
-
* @example Bill
|
|
6413
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6414
|
+
* @enum {string}
|
|
4720
6415
|
*/
|
|
4721
|
-
|
|
6416
|
+
type: 'noul';
|
|
4722
6417
|
}
|
|
4723
6418
|
|
|
4724
|
-
export interface
|
|
6419
|
+
export interface DecisionsChoiceQuestion {
|
|
4725
6420
|
/**
|
|
4726
|
-
*
|
|
4727
|
-
* @description
|
|
6421
|
+
* Criteria
|
|
6422
|
+
* @description Answer options mapped to descriptions of each option.
|
|
4728
6423
|
*/
|
|
4729
|
-
|
|
6424
|
+
criteria: {
|
|
6425
|
+
[key: string]: string | Record<string, never> | { [x: string]: any }[];
|
|
6426
|
+
};
|
|
4730
6427
|
/**
|
|
4731
|
-
*
|
|
4732
|
-
* @description
|
|
6428
|
+
* Instructions
|
|
6429
|
+
* @description The question, as text or structured multimodal content.
|
|
4733
6430
|
*/
|
|
4734
|
-
|
|
6431
|
+
instructions: string | Record<string, never> | { [x: string]: any }[];
|
|
4735
6432
|
/**
|
|
4736
|
-
*
|
|
4737
|
-
* @
|
|
6433
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6434
|
+
* @enum {string}
|
|
4738
6435
|
*/
|
|
4739
|
-
|
|
6436
|
+
type: 'choice';
|
|
6437
|
+
}
|
|
6438
|
+
|
|
6439
|
+
export interface DecisionsChoiceAnswer {
|
|
6440
|
+
choice: string;
|
|
6441
|
+
confidence?: number;
|
|
6442
|
+
probabilities?: {
|
|
6443
|
+
[key: string]: number;
|
|
6444
|
+
};
|
|
6445
|
+
/**
|
|
6446
|
+
* @description discriminator enum property added by openapi-typescript
|
|
6447
|
+
* @enum {string}
|
|
6448
|
+
*/
|
|
6449
|
+
type: 'choice';
|
|
4740
6450
|
}
|
|
4741
6451
|
|
|
4742
6452
|
export interface Coordinates {
|
|
@@ -5001,7 +6711,11 @@ export interface ControlLoraWeight {
|
|
|
5001
6711
|
* before merging it with the base model. Providing a dictionary as {"layer_name":layer_scale} allows per-layer lora scale settings. Layers with no scale provided will have scale 1.0.
|
|
5002
6712
|
* @default 1
|
|
5003
6713
|
*/
|
|
5004
|
-
scale?:
|
|
6714
|
+
scale?:
|
|
6715
|
+
| {
|
|
6716
|
+
[key: string]: number;
|
|
6717
|
+
}
|
|
6718
|
+
| number;
|
|
5005
6719
|
}
|
|
5006
6720
|
|
|
5007
6721
|
export interface CompletionUsage {
|
|
@@ -6385,20 +8099,13 @@ export interface Character {
|
|
|
6385
8099
|
avatar_style?: 'normal' | 'circle' | 'closeUp';
|
|
6386
8100
|
}
|
|
6387
8101
|
|
|
6388
|
-
export interface
|
|
8102
|
+
export interface CapacityInput {
|
|
6389
8103
|
/**
|
|
6390
|
-
*
|
|
6391
|
-
* @description The type of camera movement
|
|
6392
|
-
* @example horizontal
|
|
8104
|
+
* Unit
|
|
6393
8105
|
* @enum {string}
|
|
6394
8106
|
*/
|
|
6395
|
-
|
|
6396
|
-
|
|
6397
|
-
* Movement Value
|
|
6398
|
-
* @description The value of the camera movement
|
|
6399
|
-
* @example 10
|
|
6400
|
-
*/
|
|
6401
|
-
movement_value: number;
|
|
8107
|
+
unit: 'fl_oz' | 'ml' | 'l' | 'qt' | 'gal' | 'cups';
|
|
8108
|
+
value: number;
|
|
6402
8109
|
}
|
|
6403
8110
|
|
|
6404
8111
|
export interface BoxPromptBase_1 {
|
|
@@ -6522,6 +8229,33 @@ export interface BoxPrompt {
|
|
|
6522
8229
|
y_min?: number;
|
|
6523
8230
|
}
|
|
6524
8231
|
|
|
8232
|
+
export interface Box {
|
|
8233
|
+
/**
|
|
8234
|
+
* X Max
|
|
8235
|
+
* @description Right edge as a fraction of the image width (0-1).
|
|
8236
|
+
* @example 0.7
|
|
8237
|
+
*/
|
|
8238
|
+
x_max: number;
|
|
8239
|
+
/**
|
|
8240
|
+
* X Min
|
|
8241
|
+
* @description Left edge as a fraction of the image width (0-1).
|
|
8242
|
+
* @example 0.3
|
|
8243
|
+
*/
|
|
8244
|
+
x_min: number;
|
|
8245
|
+
/**
|
|
8246
|
+
* Y Max
|
|
8247
|
+
* @description Bottom edge as a fraction of the image height (0-1).
|
|
8248
|
+
* @example 0.9
|
|
8249
|
+
*/
|
|
8250
|
+
y_max: number;
|
|
8251
|
+
/**
|
|
8252
|
+
* Y Min
|
|
8253
|
+
* @description Top edge as a fraction of the image height (0-1).
|
|
8254
|
+
* @example 0.4
|
|
8255
|
+
*/
|
|
8256
|
+
y_min: number;
|
|
8257
|
+
}
|
|
8258
|
+
|
|
6525
8259
|
export interface BoundingBoxes {
|
|
6526
8260
|
/**
|
|
6527
8261
|
* Bboxes
|
|
@@ -6530,9 +8264,25 @@ export interface BoundingBoxes {
|
|
|
6530
8264
|
bboxes: BoundingBox_1[];
|
|
6531
8265
|
}
|
|
6532
8266
|
|
|
8267
|
+
export interface BoundingBox_2 {
|
|
8268
|
+
bottom_right: Point_1;
|
|
8269
|
+
top_left: Point_1;
|
|
8270
|
+
}
|
|
8271
|
+
|
|
6533
8272
|
export interface BoundingBox_1 {
|
|
6534
|
-
|
|
6535
|
-
|
|
8273
|
+
box: Box;
|
|
8274
|
+
/**
|
|
8275
|
+
* Description
|
|
8276
|
+
* @description What to draw in this box: the object and its look.
|
|
8277
|
+
* @example a red fox with thick orange fur and a white-tipped tail
|
|
8278
|
+
*/
|
|
8279
|
+
description: string;
|
|
8280
|
+
/**
|
|
8281
|
+
* Label
|
|
8282
|
+
* @description Short name for the object in this box, e.g. `fox`. Write `<fox>` in the prompt to tie the box to those words; a box the prompt doesn't name is added to the scene. Defaults to `obj_<n>`.
|
|
8283
|
+
* @example fox
|
|
8284
|
+
*/
|
|
8285
|
+
label?: string;
|
|
6536
8286
|
}
|
|
6537
8287
|
|
|
6538
8288
|
export interface BoundingBox {
|
|
@@ -6599,6 +8349,79 @@ export interface BasicAnimations {
|
|
|
6599
8349
|
walking_glb?: File;
|
|
6600
8350
|
}
|
|
6601
8351
|
|
|
8352
|
+
export interface Background {
|
|
8353
|
+
/**
|
|
8354
|
+
* @description Solid background color (R/G/B, 0–255). Applies when mode is 'Color'. Defaults to white.
|
|
8355
|
+
* @default {
|
|
8356
|
+
* "g": 255,
|
|
8357
|
+
* "r": 255,
|
|
8358
|
+
* "b": 255
|
|
8359
|
+
* }
|
|
8360
|
+
*/
|
|
8361
|
+
color?: RGBColor;
|
|
8362
|
+
/**
|
|
8363
|
+
* Image Fit
|
|
8364
|
+
* @description How the background image fills the canvas: 'Cover' fills and crops, 'Contain' fits and letterboxes onto `color`, 'Stretch' distorts to fit.
|
|
8365
|
+
* @default Cover
|
|
8366
|
+
* @example Cover
|
|
8367
|
+
* @enum {string}
|
|
8368
|
+
*/
|
|
8369
|
+
image_fit?: 'Cover' | 'Contain' | 'Stretch';
|
|
8370
|
+
/**
|
|
8371
|
+
* Image Url
|
|
8372
|
+
* @description Background image URL. Required when mode is 'Image'.
|
|
8373
|
+
*/
|
|
8374
|
+
image_url?: string;
|
|
8375
|
+
/**
|
|
8376
|
+
* Mode
|
|
8377
|
+
* @description 'Color' fills with `color` (white by default); 'Transparent' leaves it transparent (always PNG); 'Image' composites onto `image_url`.
|
|
8378
|
+
* @default Color
|
|
8379
|
+
* @enum {string}
|
|
8380
|
+
*/
|
|
8381
|
+
mode?: 'Transparent' | 'Color' | 'Image';
|
|
8382
|
+
}
|
|
8383
|
+
|
|
8384
|
+
export interface AvatarVWatermark {
|
|
8385
|
+
/**
|
|
8386
|
+
* Image Url
|
|
8387
|
+
* @description HTTP(S) URL of the watermark image to overlay on the video.
|
|
8388
|
+
*/
|
|
8389
|
+
image_url: string;
|
|
8390
|
+
/**
|
|
8391
|
+
* Opacity
|
|
8392
|
+
* @description Watermark opacity (0.0 = transparent, 1.0 = opaque).
|
|
8393
|
+
*/
|
|
8394
|
+
opacity?: number;
|
|
8395
|
+
/**
|
|
8396
|
+
* Placement
|
|
8397
|
+
* @description Where to place the watermark on the video.
|
|
8398
|
+
*/
|
|
8399
|
+
placement?: 'top-left' | 'top-right' | 'bottom-left' | 'bottom-right';
|
|
8400
|
+
/**
|
|
8401
|
+
* Scale
|
|
8402
|
+
* @description Watermark scale relative to the video (0.0 exclusive–2.0).
|
|
8403
|
+
*/
|
|
8404
|
+
scale?: number;
|
|
8405
|
+
}
|
|
8406
|
+
|
|
8407
|
+
export interface AvatarVBackground {
|
|
8408
|
+
/**
|
|
8409
|
+
* Type
|
|
8410
|
+
* @description Type of background. 'color' for a solid hex color, 'image' for an image URL.
|
|
8411
|
+
* @default color
|
|
8412
|
+
* @enum {string}
|
|
8413
|
+
*/
|
|
8414
|
+
type?: 'color' | 'image';
|
|
8415
|
+
/**
|
|
8416
|
+
* Value
|
|
8417
|
+
* @description Background value — hex color for 'color' type, or HTTP(S) URL for 'image' type.
|
|
8418
|
+
* @default #FFFFFF
|
|
8419
|
+
* @example #FFFFFF
|
|
8420
|
+
* @example https://example.com/background.jpg
|
|
8421
|
+
*/
|
|
8422
|
+
value?: string;
|
|
8423
|
+
}
|
|
8424
|
+
|
|
6602
8425
|
export interface AvatarIVBackground {
|
|
6603
8426
|
/**
|
|
6604
8427
|
* Type
|
|
@@ -6615,6 +8438,52 @@ export interface AvatarIVBackground {
|
|
|
6615
8438
|
value?: string;
|
|
6616
8439
|
}
|
|
6617
8440
|
|
|
8441
|
+
export interface AV2AVValidation {
|
|
8442
|
+
/**
|
|
8443
|
+
* Prompt
|
|
8444
|
+
* @description The prompt to use for validation.
|
|
8445
|
+
*/
|
|
8446
|
+
prompt: string;
|
|
8447
|
+
/**
|
|
8448
|
+
* Reference Audio Url
|
|
8449
|
+
* @description Optional URL to a separate reference audio. If omitted, the audio is taken from reference_video_url's own track.
|
|
8450
|
+
*/
|
|
8451
|
+
reference_audio_url?: string;
|
|
8452
|
+
/**
|
|
8453
|
+
* Reference Video Url
|
|
8454
|
+
* @description URL to the reference video (its audio track is also used as the audio reference) that conditions the generated audio+video.
|
|
8455
|
+
*/
|
|
8456
|
+
reference_video_url: string;
|
|
8457
|
+
}
|
|
8458
|
+
|
|
8459
|
+
export interface AV2AVMaskedValidation {
|
|
8460
|
+
/**
|
|
8461
|
+
* Mask Url
|
|
8462
|
+
* @description URL to the mask (image or video). WHITE marks the region to regenerate, BLACK is kept unchanged.
|
|
8463
|
+
*/
|
|
8464
|
+
mask_url: string;
|
|
8465
|
+
/**
|
|
8466
|
+
* Prompt
|
|
8467
|
+
* @description The prompt to use for validation.
|
|
8468
|
+
*/
|
|
8469
|
+
prompt: string;
|
|
8470
|
+
/**
|
|
8471
|
+
* Reference Audio Url
|
|
8472
|
+
* @description Optional URL to a separate reference audio. If omitted, the audio is taken from reference_video_url's own track.
|
|
8473
|
+
*/
|
|
8474
|
+
reference_audio_url?: string;
|
|
8475
|
+
/**
|
|
8476
|
+
* Reference Video Url
|
|
8477
|
+
* @description URL to the reference video (its audio track is also used as the audio reference) guiding the regenerated audio+video.
|
|
8478
|
+
*/
|
|
8479
|
+
reference_video_url: string;
|
|
8480
|
+
/**
|
|
8481
|
+
* Video Url
|
|
8482
|
+
* @description URL to the source video. Its UNMASKED region is kept pixel-faithful and the masked region is regenerated.
|
|
8483
|
+
*/
|
|
8484
|
+
video_url: string;
|
|
8485
|
+
}
|
|
8486
|
+
|
|
6618
8487
|
export interface AudioTrack {
|
|
6619
8488
|
/**
|
|
6620
8489
|
* Bitrate
|
|
@@ -6740,6 +8609,30 @@ export interface AudioSetting {
|
|
|
6740
8609
|
sample_rate?: 8000 | 16000 | 22050 | 24000 | 32000 | 44100;
|
|
6741
8610
|
}
|
|
6742
8611
|
|
|
8612
|
+
export interface AudioInpaintValidation {
|
|
8613
|
+
/**
|
|
8614
|
+
* Audio Url
|
|
8615
|
+
* @description URL to the audio clip to inpaint.
|
|
8616
|
+
*/
|
|
8617
|
+
audio_url: string;
|
|
8618
|
+
/**
|
|
8619
|
+
* Prompt
|
|
8620
|
+
* @description The prompt to use for validation.
|
|
8621
|
+
*/
|
|
8622
|
+
prompt: string;
|
|
8623
|
+
/**
|
|
8624
|
+
* Time Ranges
|
|
8625
|
+
* @description Time ranges (in seconds, [start, end]) to REGENERATE/inpaint; the rest of the audio is kept. e.g. [[1.0, 2.0]].
|
|
8626
|
+
* @example [
|
|
8627
|
+
* [
|
|
8628
|
+
* 1,
|
|
8629
|
+
* 2
|
|
8630
|
+
* ]
|
|
8631
|
+
* ]
|
|
8632
|
+
*/
|
|
8633
|
+
time_ranges: [number, number][];
|
|
8634
|
+
}
|
|
8635
|
+
|
|
6743
8636
|
export interface AudioFile_2 {
|
|
6744
8637
|
/**
|
|
6745
8638
|
* Content Type
|
|
@@ -6835,7 +8728,20 @@ export interface AudioFile {
|
|
|
6835
8728
|
url: string;
|
|
6836
8729
|
}
|
|
6837
8730
|
|
|
6838
|
-
export interface
|
|
8731
|
+
export interface AudioExtendValidation {
|
|
8732
|
+
/**
|
|
8733
|
+
* Audio Url
|
|
8734
|
+
* @description URL to the audio clip the model should temporally extend.
|
|
8735
|
+
*/
|
|
8736
|
+
audio_url: string;
|
|
8737
|
+
/**
|
|
8738
|
+
* Prompt
|
|
8739
|
+
* @description The prompt to use for validation.
|
|
8740
|
+
*/
|
|
8741
|
+
prompt: string;
|
|
8742
|
+
}
|
|
8743
|
+
|
|
8744
|
+
export interface Audio_1 {
|
|
6839
8745
|
/**
|
|
6840
8746
|
* Bitrate
|
|
6841
8747
|
* @description Overall bitrate of the media in bits per second
|
|
@@ -6895,6 +8801,38 @@ export interface Audio {
|
|
|
6895
8801
|
url: string;
|
|
6896
8802
|
}
|
|
6897
8803
|
|
|
8804
|
+
export interface Audio {
|
|
8805
|
+
/**
|
|
8806
|
+
* Content Type
|
|
8807
|
+
* @description The mime type of the file.
|
|
8808
|
+
* @example image/png
|
|
8809
|
+
*/
|
|
8810
|
+
content_type?: string;
|
|
8811
|
+
/**
|
|
8812
|
+
* File Data
|
|
8813
|
+
* Format: binary
|
|
8814
|
+
* @description File data
|
|
8815
|
+
*/
|
|
8816
|
+
file_data?: string;
|
|
8817
|
+
/**
|
|
8818
|
+
* File Name
|
|
8819
|
+
* @description The name of the file. It will be auto-generated if not provided.
|
|
8820
|
+
* @example z9RV14K95DvU.png
|
|
8821
|
+
*/
|
|
8822
|
+
file_name?: string;
|
|
8823
|
+
/**
|
|
8824
|
+
* File Size
|
|
8825
|
+
* @description The size of the file in bytes.
|
|
8826
|
+
* @example 4404019
|
|
8827
|
+
*/
|
|
8828
|
+
file_size?: number;
|
|
8829
|
+
/**
|
|
8830
|
+
* Url
|
|
8831
|
+
* @description The URL where the file can be downloaded from.
|
|
8832
|
+
*/
|
|
8833
|
+
url: string;
|
|
8834
|
+
}
|
|
8835
|
+
|
|
6898
8836
|
export interface AspectRatio {
|
|
6899
8837
|
/**
|
|
6900
8838
|
* Ratio
|
|
@@ -6905,6 +8843,25 @@ export interface AspectRatio {
|
|
|
6905
8843
|
ratio?: '1:1' | '16:9' | '9:16' | '4:3' | '3:4';
|
|
6906
8844
|
}
|
|
6907
8845
|
|
|
8846
|
+
export interface AnswerOutput {
|
|
8847
|
+
sdp: string;
|
|
8848
|
+
/**
|
|
8849
|
+
* @description discriminator enum property added by openapi-typescript
|
|
8850
|
+
* @enum {string}
|
|
8851
|
+
*/
|
|
8852
|
+
type: 'answer';
|
|
8853
|
+
}
|
|
8854
|
+
|
|
8855
|
+
export interface AnimationClip {
|
|
8856
|
+
/**
|
|
8857
|
+
* Action Id
|
|
8858
|
+
* @description The Meshy animation preset action ID applied to this clip.
|
|
8859
|
+
*/
|
|
8860
|
+
action_id: number;
|
|
8861
|
+
animation_fbx?: File;
|
|
8862
|
+
animation_glb?: File;
|
|
8863
|
+
}
|
|
8864
|
+
|
|
6908
8865
|
export interface AestheticsDetails {
|
|
6909
8866
|
/**
|
|
6910
8867
|
* Aesthetic Score
|
|
@@ -6933,12 +8890,12 @@ export interface AestheticsDetails {
|
|
|
6933
8890
|
preference_score: string;
|
|
6934
8891
|
}
|
|
6935
8892
|
|
|
6936
|
-
export interface
|
|
8893
|
+
export interface Aesthetics_1 {
|
|
6937
8894
|
/**
|
|
6938
8895
|
* Aesthetic Score
|
|
6939
|
-
* @description The aesthetic score of the image.
|
|
8896
|
+
* @description The aesthetic score of the image (e.g., 'very high', 'high', 'medium', 'low').
|
|
6940
8897
|
*/
|
|
6941
|
-
aesthetic_score
|
|
8898
|
+
aesthetic_score?: string;
|
|
6942
8899
|
/**
|
|
6943
8900
|
* Color Scheme
|
|
6944
8901
|
* @description The color scheme of the image to be generated.
|
|
@@ -6956,15 +8913,16 @@ export interface Aesthetics_2 {
|
|
|
6956
8913
|
mood_atmosphere?: string;
|
|
6957
8914
|
/**
|
|
6958
8915
|
* Preference Score
|
|
6959
|
-
* @description The preference score of the image.
|
|
8916
|
+
* @description The preference score of the image (e.g., 'very high', 'high', 'medium', 'low').
|
|
6960
8917
|
*/
|
|
6961
|
-
preference_score
|
|
8918
|
+
preference_score?: string;
|
|
8919
|
+
[key: string]: any;
|
|
6962
8920
|
}
|
|
6963
8921
|
|
|
6964
|
-
export
|
|
8922
|
+
export interface Aesthetics {
|
|
6965
8923
|
/**
|
|
6966
8924
|
* Aesthetic Score
|
|
6967
|
-
* @description The aesthetic score of the image
|
|
8925
|
+
* @description The aesthetic score of the image to be generated.
|
|
6968
8926
|
*/
|
|
6969
8927
|
aesthetic_score?: string;
|
|
6970
8928
|
/**
|
|
@@ -6984,29 +8942,40 @@ export type Aesthetics_1 = {
|
|
|
6984
8942
|
mood_atmosphere?: string;
|
|
6985
8943
|
/**
|
|
6986
8944
|
* Preference Score
|
|
6987
|
-
* @description The preference score of the image
|
|
8945
|
+
* @description The preference score of the image to be generated.
|
|
6988
8946
|
*/
|
|
6989
8947
|
preference_score?: string;
|
|
6990
|
-
}
|
|
6991
|
-
[key: string]: { [x: string]: any } | null;
|
|
6992
|
-
};
|
|
8948
|
+
}
|
|
6993
8949
|
|
|
6994
|
-
export interface
|
|
8950
|
+
export interface A2VValidation {
|
|
6995
8951
|
/**
|
|
6996
|
-
*
|
|
6997
|
-
* @description
|
|
8952
|
+
* Audio Url
|
|
8953
|
+
* @description URL to the conditioning audio track that drives the generated video.
|
|
6998
8954
|
*/
|
|
6999
|
-
|
|
8955
|
+
audio_url: string;
|
|
7000
8956
|
/**
|
|
7001
|
-
*
|
|
7002
|
-
* @description
|
|
8957
|
+
* Image Url
|
|
8958
|
+
* @description URL to the start image used as the first frame (a2v is image+audio -> video, so the model conditions on this frame and the audio rather than generating the first frame).
|
|
7003
8959
|
*/
|
|
7004
|
-
|
|
8960
|
+
image_url: string;
|
|
7005
8961
|
/**
|
|
7006
|
-
*
|
|
7007
|
-
* @description The
|
|
8962
|
+
* Prompt
|
|
8963
|
+
* @description The prompt to use for validation.
|
|
7008
8964
|
*/
|
|
7009
|
-
|
|
8965
|
+
prompt: string;
|
|
8966
|
+
}
|
|
8967
|
+
|
|
8968
|
+
export interface A2AValidation {
|
|
8969
|
+
/**
|
|
8970
|
+
* Prompt
|
|
8971
|
+
* @description The prompt to use for validation.
|
|
8972
|
+
*/
|
|
8973
|
+
prompt: string;
|
|
8974
|
+
/**
|
|
8975
|
+
* Reference Audio Url
|
|
8976
|
+
* @description URL to the reference audio that conditions the generated audio.
|
|
8977
|
+
*/
|
|
8978
|
+
reference_audio_url: string;
|
|
7010
8979
|
}
|
|
7011
8980
|
|
|
7012
8981
|
export {};
|