aliyun-pixverse-generation

Name: aliyun-pixverse-generation
Author: cinience

397stars34forks

How to install aliyun-pixverse-generation?

cinience/alicloud-skills/aliyun-pixverse-generation

$npx -y skills add cinience/alicloud-skills --skill aliyun-pixverse-generation

Installs into the current project.

Summary

Use when generating videos with Alibaba Cloud Model Studio PixVerse models (pixverse/pixverse-v5.6-t2v, pixverse/pixverse-v5.6-it2v, pixverse/pixverse-v5.6-kf2v, pixverse/pixverse-v5.6-r2v). Use when building non-Wan text-to-video, first-frame image-to-video, keyframe-to-

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Aishi Video Generation
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-pixverse-generation
9	python -m py_compile skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py && echo "py_compile_ok" > output/aliyun-pixverse-generation/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-pixverse-generation/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, chosen model variant, and task polling snapshots under `output/aliyun-pixverse-generation/`.
17	- Record region, resolution/size, duration, and whether audio generation was enabled.
18
19	Use Aishi when the user explicitly wants the non-Wan PixVerse family for video generation.
20
21	## Critical model names
22
23	Use one of these exact model strings:
24	- `pixverse/pixverse-v5.6-t2v`
25	- `pixverse/pixverse-v5.6-it2v`
26	- `pixverse/pixverse-v5.6-kf2v`
27	- `pixverse/pixverse-v5.6-r2v`
28
29	Selection guidance:
30	- Use `pixverse/pixverse-v5.6-t2v` for text-only generation.
31	- Use `pixverse/pixverse-v5.6-it2v` for first-frame image-to-video.
32	- Use `pixverse/pixverse-v5.6-kf2v` for first-frame + last-frame transitions.
33	- Use `pixverse/pixverse-v5.6-r2v` for multi-image character/style consistency.
34
35	## Prerequisites
36
37	- This family currently only supports China mainland (Beijing).
38	- Install SDK or call HTTP directly:
39
40	```bash
41	python3 -m venv .venv
42	. .venv/bin/activate
43	python -m pip install dashscope
44	```
45
46	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
47
48	## Normalized interface (video.generate)
49
50	### Request
51	- `model` (string, required)
52	- `prompt` (string, optional for `it2v`, required for other variants)
53	- `media` (array<object>, optional)
54	- `size` (string, optional): direct pixel size such as `1280*720`, used by `t2v` and `r2v`
55	- `resolution` (string, optional): `360P`/`540P`/`720P`/`1080P`, used by `it2v` and `kf2v`
56	- `duration` (int, required): `5`/`8`/`10`, except 1080P only supports `5`/`8`
57	- `audio` (bool, optional)
58	- `watermark` (bool, optional)
59	- `seed` (int, optional)
60
61	### Response
62	- `task_id` (string)
63	- `task_status` (string)
64	- `video_url` (string, when finished)
65
66	## Endpoint and execution model
67
68	- Submit task: `POST https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis`
69	- Poll task: `GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}`
70	- HTTP calls are async only and must set header `X-DashScope-Async: enable`.
71
72	## Quick start
73
74	Text-to-video:
75
76	```bash
77	python skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py \
78	--model pixverse/pixverse-v5.6-t2v \
79	--prompt "A compact robot walks through a rainy neon alley." \
80	--size 1280*720 \
81	--duration 5
82	```
83
84	Image-to-video:
85
86	```bash
87	python skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py \
88	--model pixverse/pixverse-v5.6-it2v \
89	--prompt "The turtle swims slowly as the camera rises." \
90	--media image_url=https://example.com/turtle.webp \
91	--resolution 720P \
92	--duration 5
93	```
94
95	## Operational guidance
96
97	- `t2v` and `r2v` use `size`; `it2v` and `kf2v` use `resolution`.
98	- For `kf2v`, provide exactly one `first_frame` and one `last_frame`.
99	- For `r2v`, you can pass up to 7 reference images.
100	- Aishi returns task IDs first; do not treat the initial response as the final video result.
101
102	## Output location
103
104	- Default output: `output/aliyun-pixverse-generation/request.json`
105	- Override base dir with `OUTPUT_DIR`.
106
107	## References
108
109	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-pixverse-generation

397stars34forks

View on GitHub

How to install aliyun-pixverse-generation?

cinience/alicloud-skills/aliyun-pixverse-generation

$npx -y skills add cinience/alicloud-skills --skill aliyun-pixverse-generation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Aishi Video Generation
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-pixverse-generation
9	python -m py_compile skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py && echo "py_compile_ok" > output/aliyun-pixverse-generation/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-pixverse-generation/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, chosen model variant, and task polling snapshots under `output/aliyun-pixverse-generation/`.
17	- Record region, resolution/size, duration, and whether audio generation was enabled.
18
19	Use Aishi when the user explicitly wants the non-Wan PixVerse family for video generation.
20
21	## Critical model names
22
23	Use one of these exact model strings:
24	- `pixverse/pixverse-v5.6-t2v`
25	- `pixverse/pixverse-v5.6-it2v`
26	- `pixverse/pixverse-v5.6-kf2v`
27	- `pixverse/pixverse-v5.6-r2v`
28
29	Selection guidance:
30	- Use `pixverse/pixverse-v5.6-t2v` for text-only generation.
31	- Use `pixverse/pixverse-v5.6-it2v` for first-frame image-to-video.
32	- Use `pixverse/pixverse-v5.6-kf2v` for first-frame + last-frame transitions.
33	- Use `pixverse/pixverse-v5.6-r2v` for multi-image character/style consistency.
34
35	## Prerequisites
36
37	- This family currently only supports China mainland (Beijing).
38	- Install SDK or call HTTP directly:
39
40	```bash
41	python3 -m venv .venv
42	. .venv/bin/activate
43	python -m pip install dashscope
44	```
45
46	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
47
48	## Normalized interface (video.generate)
49
50	### Request
51	- `model` (string, required)
52	- `prompt` (string, optional for `it2v`, required for other variants)
53	- `media` (array<object>, optional)
54	- `size` (string, optional): direct pixel size such as `1280*720`, used by `t2v` and `r2v`
55	- `resolution` (string, optional): `360P`/`540P`/`720P`/`1080P`, used by `it2v` and `kf2v`
56	- `duration` (int, required): `5`/`8`/`10`, except 1080P only supports `5`/`8`
57	- `audio` (bool, optional)
58	- `watermark` (bool, optional)
59	- `seed` (int, optional)
60
61	### Response
62	- `task_id` (string)
63	- `task_status` (string)
64	- `video_url` (string, when finished)
65
66	## Endpoint and execution model
67
68	- Submit task: `POST https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis`
69	- Poll task: `GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}`
70	- HTTP calls are async only and must set header `X-DashScope-Async: enable`.
71
72	## Quick start
73
74	Text-to-video:
75
76	```bash
77	python skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py \
78	--model pixverse/pixverse-v5.6-t2v \
79	--prompt "A compact robot walks through a rainy neon alley." \
80	--size 1280*720 \
81	--duration 5
82	```
83
84	Image-to-video:
85
86	```bash
87	python skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py \
88	--model pixverse/pixverse-v5.6-it2v \
89	--prompt "The turtle swims slowly as the camera rises." \
90	--media image_url=https://example.com/turtle.webp \
91	--resolution 720P \
92	--duration 5
93	```
94
95	## Operational guidance
96
97	- `t2v` and `r2v` use `size`; `it2v` and `kf2v` use `resolution`.
98	- For `kf2v`, provide exactly one `first_frame` and one `last_frame`.
99	- For `r2v`, you can pass up to 7 reference images.
100	- Aishi returns task IDs first; do not treat the initial response as the final video result.
101
102	## Output location
103
104	- Default output: `output/aliyun-pixverse-generation/request.json`
105	- Override base dir with `OUTPUT_DIR`.
106
107	## References
108
109	- `references/sources.md`

People who liked this also viewed

6 picks

Type