pixverse 1.3.1 → 1.3.3

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/README.md CHANGED
@@ -32,7 +32,7 @@ Or run without installing:
32
32
  npx pixverse
33
33
  ```
34
34
 
35
- **Requirements:** Node.js >= 20
35
+ **Requirements:** Node.js >= 22.12
36
36
 
37
37
  ## Authentication
38
38
 
@@ -59,18 +59,20 @@ This opens a browser where you confirm the authorization. You can also copy the
59
59
  | :---------------------- | :---------------------- | :---------------------------------- | :------------ | :------------------------------------------------- |
60
60
  | PixVerse V6 _(default)_ | `v6` | `360p` `540p` `720p` `1080p` | `1`–`15`s | `16:9` `4:3` `1:1` `3:4` `9:16` `3:2` `2:3` `21:9` |
61
61
  | PixVerse C1 | `pixverse-c1` | `360p` `540p` `720p` `1080p` | `1`–`15`s | `16:9` `4:3` `1:1` `3:4` `9:16` `3:2` `2:3` |
62
- | Seedance 2.5 | `seedance-2.5` | `480p` `720p` | `4`–`30`s | `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` |
62
+ | Seedance 2.5 | `seedance-2.5` | `480p` `720p` | `4`–`30`s | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` |
63
63
  | Seedance 2.0 Standard | `seedance-2.0-standard` | `480p` `720p` `1080p` `2160p` | `4`–`15`s | `16:9` `4:3` `1:1` `3:4` `9:16` `21:9` |
64
64
  | Seedance 2.0 Fast | `seedance-2.0-fast` | `480p` `720p` | `4`–`15`s | `16:9` `4:3` `1:1` `3:4` `9:16` `21:9` |
65
65
  | Seedance 2.0 Mini | `seedance-2.0-mini` | `480p` `720p` | `4`–`15`s | `16:9` `4:3` `1:1` `3:4` `9:16` `21:9` |
66
66
  | MiniMax H3 | `minimax-h3` | `768p` `1440p` | `5`–`15`s | `auto` `21:9` `16:9` `4:3` `1:1` `3:4` `9:16` |
67
67
  | Google Gemini Omni | `gemini-omni-flash` | `720p` | `3`–`10`s | `16:9` `9:16` |
68
68
  | Happy Horse 1.0 | `happyhorse-1.0` | `720p` `1080p` | `3`–`15`s | `16:9` `9:16` `1:1` `4:3` `3:4` |
69
- | Kling O3 Pro | `kling-o3-pro` | `720p` | `3`–`15`s | `16:9` `9:16` `1:1` |
70
- | Kling O3 Standard | `kling-o3-standard` | `720p` | `3`–`15`s | `16:9` `9:16` `1:1` |
71
- | Kling 3.0 Pro | `kling-3.0-pro` | `720p` | `3`–`15`s | `16:9` `9:16` `1:1` |
72
- | Kling 3.0 Standard | `kling-3.0-standard` | `720p` | `3`–`15`s | `16:9` `9:16` `1:1` |
73
- | Grok Imagine 1.5 | `grok-imagine-1.5` | `480p` `720p` | `1`–`15`s | _from image_ |
69
+ | Kling O3 Pro | `kling-o3-pro` | _not applicable_ | `3`–`15`s | `16:9` `9:16` `1:1` |
70
+ | Kling O3 Standard | `kling-o3-standard` | _not applicable_ | `3`–`15`s | `16:9` `9:16` `1:1` |
71
+ | Kling O3 4K | `kling-o3-4k` | _not applicable_ | `3`–`15`s | `16:9` `9:16` `1:1` |
72
+ | Kling 3.0 Pro | `kling-3.0-pro` | _not applicable_ | `3`–`15`s | `16:9` `9:16` `1:1` |
73
+ | Kling 3.0 Standard | `kling-3.0-standard` | _not applicable_ | `3`–`15`s | `16:9` `9:16` `1:1` |
74
+ | Kling 3.0 4K | `kling-3.0-4k` | _not applicable_ | `3`–`15`s | `16:9` `9:16` `1:1` |
75
+ | Grok Imagine 1.5 | `grok-imagine-1.5` | `480p` `720p` `1080p` | `1`–`15`s | _from image_ |
74
76
  | Grok Imagine | `grok-imagine` | `480p` `720p` | `1`–`15`s | `16:9` `4:3` `1:1` `9:16` `3:4` `3:2` `2:3` |
75
77
  | Veo 3.1 Lite | `veo-3.1-lite` | `720p` `1080p` | `4` `6` `8`s | `16:9` `9:16` |
76
78
  | Veo 3.1 Standard | `veo-3.1-standard` | `720p` `1080p` `2160p` | `4` `6` `8`s | `16:9` `9:16` |
@@ -81,25 +83,29 @@ This opens a browser where you confirm the authorization. You can also copy the
81
83
  | PixVerse v5.5 | `v5.5` | `360p` `480p` `540p` `720p` `1080p` | `1`–`10`s | `16:9` `4:3` `1:1` `3:4` `9:16` `3:2` `2:3` |
82
84
  | PixVerse v5 | `v5` | `360p` `480p` `540p` `720p` `1080p` | `1`–`10`s | `16:9` `4:3` `1:1` `3:4` `9:16` `3:2` `2:3` |
83
85
 
84
- > Seedance 2.5 defaults to `720p`, 5 seconds, and `16:9`. Text-to-video, image-to-video, and reference mode accept its fixed aspect ratios. Transition does not send a user-selected aspect ratio. Generated audio, multi-shot, and off-peak generation are unsupported.
86
+ > Seedance 2.5 defaults to `720p`, 5 seconds, and `16:9` for generation without a reference video. Text-to-video and reference mode accept `--aspect-ratio auto` in addition to the fixed ratios. Reference requests containing a video default to automatic duration and lock the aspect ratio to `auto`; selecting an integer from 4 through 30 unlocks both automatic and fixed aspect ratios. Reference mode also accepts the optional `--task-type <type>` flag (`auto` by default, `reference`, `edit`, or `extend`) to guide the task intent; this flag is rejected for other models. Image-to-video retains its existing fixed-ratio behavior, while transition does not send a user-selected aspect ratio. Generated audio, multi-shot, and off-peak generation are unsupported.
85
87
 
86
88
  > MiniMax H3 text-to-video defaults to `16:9`. Image-to-video forces `auto`; reference mode with images supports both `auto` and fixed aspect ratios and defaults to `auto`.
87
89
 
88
- > Grok Imagine 1.5 is image-to-video only it requires `--image` and derives its aspect ratio from the input image (the `--aspect-ratio` flag is ignored).
90
+ > Kling resolution is selected entirely by the model ID. Kling requests do not send `quality`; an explicit `--quality` value is ignored with a warning. Both 4K models support text/image-to-video and two-frame transitions, while only Kling O3 4K supports `create reference`.
91
+
92
+ > Reference video editing: V6 accepts up to 10 images and 2 videos (15s total after per-clip rounding); requests with a video lock duration to `auto` and reject fixed values. Seedance 2.5 accepts up to 10 videos (30s total); requests with a video default to `auto` but may select a fixed 4–30 seconds. Gemini Omni accepts up to 5 images and 1 video up to 10s; requests with a video lock duration to `auto` and reject fixed values. Kling O3 accepts up to 7 images without video or 4 images with 1 video up to 15s (200MB, 2048px per side). Grok Imagine accepts either 1–7 images with normal fixed duration or exactly 1 MP4 video up to 8.7s; video mode locks duration to `auto` and derives aspect ratio from the source video.
93
+
94
+ > Grok Imagine 1.5 is image-to-video only — it requires `--image`, supports `480p`, `720p`, and `1080p`, and derives its aspect ratio from the input image (the `--aspect-ratio` flag is ignored).
89
95
 
90
96
  > Not all models support all creation modes. See the per-mode support matrix below.
91
97
 
92
98
  #### Per-mode Model Support
93
99
 
94
- | Creation mode | Supported `--model` values |
95
- | :---------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
96
- | `create video` (text-to-video / image-to-video) | `v6` `pixverse-c1` `seedance-2.5` `seedance-2.0-standard` `seedance-2.0-fast` `seedance-2.0-mini` `minimax-h3` `gemini-omni-flash` `happyhorse-1.0` `kling-o3-pro` `kling-o3-standard` `kling-3.0-pro` `kling-3.0-standard` `grok-imagine-1.5` `grok-imagine` `veo-3.1-lite` `veo-3.1-standard` `veo-3.1-fast` `sora-2-pro` `sora-2` `v5.6` |
97
- | `create extend` | `v6` `grok-imagine` |
98
- | `create reference` (multi-subject reference) | `v6` `pixverse-c1` `seedance-2.5` `seedance-2.0-standard` `seedance-2.0-fast` `seedance-2.0-mini` `minimax-h3` `gemini-omni-flash` `kling-o3-pro` `kling-o3-standard` `grok-imagine` `v5.6` |
99
- | `create transition` (2 frames) | `v6` `pixverse-c1` `seedance-2.5` `seedance-2.0-standard` `seedance-2.0-fast` `seedance-2.0-mini` `minimax-h3` `kling-o3-pro` `kling-o3-standard` `kling-3.0-pro` `kling-3.0-standard` `veo-3.1-lite` `veo-3.1-standard` `veo-3.1-fast` `v5.6` |
100
- | `create transition` (3+ frames) | `v5` |
101
- | `create modify` | `v5.5` |
102
- | `create motion-control` | `v5.6` |
100
+ | Creation mode | Supported `--model` values |
101
+ | :---------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
102
+ | `create video` (text-to-video / image-to-video) | `v6` `pixverse-c1` `seedance-2.5` `seedance-2.0-standard` `seedance-2.0-fast` `seedance-2.0-mini` `minimax-h3` `gemini-omni-flash` `happyhorse-1.0` `kling-o3-pro` `kling-o3-standard` `kling-o3-4k` `kling-3.0-pro` `kling-3.0-standard` `kling-3.0-4k` `grok-imagine-1.5` `grok-imagine` `veo-3.1-lite` `veo-3.1-standard` `veo-3.1-fast` `sora-2-pro` `sora-2` `v5.6` |
103
+ | `create extend` | `v6` `grok-imagine` |
104
+ | `create reference` (reference / video editing) | `v6` `pixverse-c1` `seedance-2.5` `seedance-2.0-standard` `seedance-2.0-fast` `seedance-2.0-mini` `minimax-h3` `gemini-omni-flash` `kling-o3-pro` `kling-o3-standard` `kling-o3-4k` `grok-imagine` `v5.6` |
105
+ | `create transition` (2 frames) | `v6` `pixverse-c1` `seedance-2.5` `seedance-2.0-standard` `seedance-2.0-fast` `seedance-2.0-mini` `minimax-h3` `kling-o3-pro` `kling-o3-standard` `kling-o3-4k` `kling-3.0-pro` `kling-3.0-standard` `kling-3.0-4k` `veo-3.1-lite` `veo-3.1-standard` `veo-3.1-fast` `v5.6` |
106
+ | `create transition` (3+ frames) | `v5` |
107
+ | `create modify` | `v5.5` |
108
+ | `create motion-control` | `v5.6` |
103
109
 
104
110
  > Audio creation uses separate model families: `create voice` for text-to-speech and `create music` for prompt-to-music.
105
111
 
@@ -166,6 +172,9 @@ pixverse create video --prompt "A cat walking on Mars" --model v6 --quality 720p
166
172
 
167
173
  # Seedance 2.5 supports integer durations from 4 through 30 seconds
168
174
  pixverse create video --prompt "A slow aerial orbit around an alpine lake" --model seedance-2.5 --quality 720p --duration 12 --aspect-ratio 21:9
175
+
176
+ # Seedance 2.5 can let the model determine the text-to-video aspect ratio
177
+ pixverse create video --prompt "A cinematic landscape revealed through fog" --model seedance-2.5 --aspect-ratio auto
169
178
  ```
170
179
 
171
180
  ### Text inputs: literal, a file, or stdin
@@ -241,12 +250,25 @@ pixverse create modify --video <video_id> --prompt "Change the background to a b
241
250
  # Upscale video resolution
242
251
  pixverse create upscale --video <video_id> --quality 2160p
243
252
 
244
- # Generate video with character reference (1–7 images)
245
- pixverse create reference --images ./char1.png ./char2.png --prompt "Two friends walking in a park"
253
+ # Generate video from image references (V6 accepts up to 10 images)
254
+ pixverse create reference -m v6 --images ./char1.png ./char2.png --prompt "Two friends walking in a park"
255
+
256
+ # Edit video with V6 reference media (up to 2 videos, rounded total ≤ 15s)
257
+ pixverse create reference -m v6 --videos ./shot1.mp4 ./shot2.mov --duration auto --prompt "Turn the scene into a rainy night"
258
+
259
+ # Gemini Omni defaults to automatic duration with its single source video (up to 10s)
260
+ pixverse create reference -m gemini-omni-flash --images ./style.png --videos ./source.mp4 --prompt "Keep @video1's motion and apply @image1's style"
261
+
262
+ # Kling O3 4K accepts up to 4 images when a video is present (video ≤ 15s, 200MB, 2048px per side)
263
+ pixverse create reference -m kling-o3-4k --images ./character.png --videos ./motion.mov --prompt "Use @image1 as the subject in @video1"
264
+
265
+ # Grok Imagine accepts images or one MP4 video, but not both (video ≤ 8.7s)
266
+ pixverse create reference -m grok-imagine --videos ./source.mp4 --prompt "Replace the background with a desert"
246
267
 
247
268
  # Seedance 2.5 reference — up to 50 total inputs: 30 images, 10 videos, and 10 audios;
248
- # video and audio totals are each limited to 30s, and audio needs an image or video
249
- pixverse create reference -m seedance-2.5 --images ./char.png --videos ./motion.mp4 --audios ./voice.mp3 --aspect-ratio 16:9 --prompt "@image1 follows @video1 and @audio1"
269
+ # video and audio totals are each limited to 30s, audio needs an image or video,
270
+ # and --task-type defaults to auto (or explicitly accepts reference, edit, or extend)
271
+ pixverse create reference -m seedance-2.5 --images ./char.png --videos ./motion.mp4 --audios ./voice.mp3 --duration auto --aspect-ratio auto --prompt "@image1 follows @video1 and @audio1"
250
272
 
251
273
  # Seedance 2.0 reference — mix images and videos (max 3 videos, total ≤ 15s)
252
274
  pixverse create reference -m seedance-2.0-standard --images ./char.png --videos ./motion.mp4 --prompt "@image1 follows the motion in @video1"
@@ -526,7 +548,7 @@ pixverse asset download "$VID" --dest ./output/
526
548
  | `create extend` | Extend video duration |
527
549
  | `create modify` | Modify an existing video |
528
550
  | `create upscale` | Upscale video resolution |
529
- | `create reference` | Generate video with character references |
551
+ | `create reference` | Create or edit a video with reference media |
530
552
  | `create motion-control` | Motion control with character image + reference video |
531
553
  | `create template` | Create from a template/effect |
532
554
  | `template categories` | List template categories |
@@ -5,9 +5,9 @@
5
5
  "cli": {
6
6
  "name": "pixverse",
7
7
  "package": "pixverse",
8
- "version": "1.3.1",
8
+ "version": "1.3.3",
9
9
  "binary": "pixverse",
10
- "node": ">=20",
10
+ "node": ">=22.12.0",
11
11
  "description": "PixVerse CLI - generate videos and images from the command line"
12
12
  },
13
13
  "contract": {
@@ -124,7 +124,7 @@
124
124
  "-m, --model <model>": "Video model",
125
125
  "-d, --duration <seconds>": "Duration in seconds",
126
126
  "-q, --quality <quality>": "Video quality",
127
- "--aspect-ratio <ratio>": "Aspect ratio",
127
+ "--aspect-ratio <ratio>": "Aspect ratio, or auto for model-determined framing where supported",
128
128
  "--seed <number>": "Random seed",
129
129
  "--count <number>": "Number of generations",
130
130
  "--audio": "Enable audio generation",
@@ -295,19 +295,20 @@
295
295
  },
296
296
  {
297
297
  "cmd": "pixverse create reference",
298
- "desc": "Multi-subject character reference video",
298
+ "desc": "Create or edit a video with reference media",
299
299
  "run": true,
300
300
  "auth": true,
301
301
  "effect": "creates_remote_media_asset",
302
302
  "options": {
303
- "--images <inputs...>": "Image inputs: file paths, HTTPS URLs, image IDs, or media paths (max 30 for seedance-2.5, 9 for seedance-2.0 and minimax-h3, 5 for gemini-omni-flash, otherwise 7; local oversized images are auto-resized to fit 1920x1920)",
304
- "--videos <inputs...>": "Video reference inputs (Seedance and minimax-h3): file paths, HTTPS URLs, video IDs, or media paths (seedance-2.5: max 10 and ≤30s total; others: max 3, seedance-2.0 ≤15s total)",
303
+ "--images <inputs...>": "Image references: file paths, HTTPS URLs, image IDs, or media paths (model-specific limits; local oversized images are auto-resized to fit 1920x1920)",
304
+ "--videos <inputs...>": "Video references: file paths, HTTPS URLs, video IDs, or media paths (supported by V6, Seedance, MiniMax H3, Gemini Omni, Kling O3, and Grok Imagine; model-specific limits apply)",
305
305
  "--audios <inputs...>": "Audio reference inputs (Seedance and minimax-h3): file paths, HTTPS URLs, audio IDs, or media paths (seedance-2.5: max 10 and ≤30s total; others: max 3, seedance-2.0 clips 2–15s and ≤15s total; requires an image or video)",
306
306
  "--prompt <text>": "Prompt text",
307
307
  "-m, --model <model>": "Video model",
308
+ "--task-type <type>": "Seedance 2.5 reference task type: auto, reference, edit, or extend",
308
309
  "-q, --quality <quality>": "Video quality",
309
- "--aspect-ratio <ratio>": "Aspect ratio",
310
- "-d, --duration <seconds>": "Duration in seconds",
310
+ "--aspect-ratio <ratio>": "Aspect ratio, or auto for model-determined framing where supported",
311
+ "-d, --duration <seconds|auto>": "Duration in seconds, or auto (locked for V6/Grok video references; default for Seedance 2.5 video references)",
311
312
  "--count <number>": "Number of generations",
312
313
  "--seed <number>": "Random seed",
313
314
  "--audio": "Enable audio generation",