aliyun-wan-r2v

Name: aliyun-wan-r2v
Author: cinience

397stars34forks

How to install aliyun-wan-r2v?

cinience/alicloud-skills/aliyun-wan-r2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-wan-r2v

Installs into the current project.

Summary

Use when generating reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from reference video/image material, preserving character style, or documenting reference-to-video request/response flows.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Wan R2V
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-wan-r2v
9	python -m py_compile skills/ai/video/aliyun-wan-r2v/scripts/prepare_r2v_request.py && echo "py_compile_ok" > output/aliyun-wan-r2v/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-wan-r2v/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save reference input metadata, request payloads, and task outputs in `output/aliyun-wan-r2v/`.
17	- Keep at least one polling result snapshot.
18
19	Use Wan R2V for reference-to-video generation. This is different from i2v (single image to video).
20
21	## Critical model names
22
23	Use one of these exact model strings:
24	- `wan2.6-r2v-flash`
25	- `wan2.6-r2v`
26
27	Newer official releases may prefer the flash variant for lower latency and lower cost.
28
29	## Prerequisites
30
31	- Install SDK in a virtual environment:
32
33	```bash
34	python3 -m venv .venv
35	. .venv/bin/activate
36	python -m pip install dashscope
37	```
38	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
39
40	## Normalized interface (video.generate_reference)
41
42	### Request
43	- `prompt` (string, required)
44	- `reference_video` (string \| bytes, required)
45	- `reference_image` (string \| bytes, optional)
46	- `duration` (number, optional)
47	- `fps` (number, optional)
48	- `size` (string, optional)
49	- `seed` (int, optional)
50
51	### Response
52	- `video_url` (string)
53	- `task_id` (string, when async)
54	- `request_id` (string)
55
56	## Async handling
57
58	- Prefer async submission for production traffic.
59	- Poll task result with 15-20s intervals.
60	- Stop polling when `SUCCEEDED` or terminal failure status is returned.
61
62	## Local helper script
63
64	Prepare a normalized request JSON and validate response schema:
65
66	```bash
67	.venv/bin/python skills/ai/video/aliyun-wan-r2v/scripts/prepare_r2v_request.py \
68	--prompt "Generate a short montage with consistent character style" \
69	--reference-video "https://example.com/reference.mp4"
70	```
71
72	## Output location
73
74	- Default output: `output/aliyun-wan-r2v/videos/`
75	- Override base dir with `OUTPUT_DIR`.
76
77	## Workflow
78
79	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
80	2) Run one minimal read-only query first to verify connectivity and permissions.
81	3) Execute the target operation with explicit parameters and bounded scope.
82	4) Verify results and save output/evidence files.
83
84	## References
85
86	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-wan-r2v

397stars34forks

View on GitHub

How to install aliyun-wan-r2v?

cinience/alicloud-skills/aliyun-wan-r2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-wan-r2v

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Wan R2V
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-wan-r2v
9	python -m py_compile skills/ai/video/aliyun-wan-r2v/scripts/prepare_r2v_request.py && echo "py_compile_ok" > output/aliyun-wan-r2v/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-wan-r2v/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save reference input metadata, request payloads, and task outputs in `output/aliyun-wan-r2v/`.
17	- Keep at least one polling result snapshot.
18
19	Use Wan R2V for reference-to-video generation. This is different from i2v (single image to video).
20
21	## Critical model names
22
23	Use one of these exact model strings:
24	- `wan2.6-r2v-flash`
25	- `wan2.6-r2v`
26
27	Newer official releases may prefer the flash variant for lower latency and lower cost.
28
29	## Prerequisites
30
31	- Install SDK in a virtual environment:
32
33	```bash
34	python3 -m venv .venv
35	. .venv/bin/activate
36	python -m pip install dashscope
37	```
38	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
39
40	## Normalized interface (video.generate_reference)
41
42	### Request
43	- `prompt` (string, required)
44	- `reference_video` (string \| bytes, required)
45	- `reference_image` (string \| bytes, optional)
46	- `duration` (number, optional)
47	- `fps` (number, optional)
48	- `size` (string, optional)
49	- `seed` (int, optional)
50
51	### Response
52	- `video_url` (string)
53	- `task_id` (string, when async)
54	- `request_id` (string)
55
56	## Async handling
57
58	- Prefer async submission for production traffic.
59	- Poll task result with 15-20s intervals.
60	- Stop polling when `SUCCEEDED` or terminal failure status is returned.
61
62	## Local helper script
63
64	Prepare a normalized request JSON and validate response schema:
65
66	```bash
67	.venv/bin/python skills/ai/video/aliyun-wan-r2v/scripts/prepare_r2v_request.py \
68	--prompt "Generate a short montage with consistent character style" \
69	--reference-video "https://example.com/reference.mp4"
70	```
71
72	## Output location
73
74	- Default output: `output/aliyun-wan-r2v/videos/`
75	- Override base dir with `OUTPUT_DIR`.
76
77	## Workflow
78
79	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
80	2) Run one minimal read-only query first to verify connectivity and permissions.
81	3) Execute the target operation with explicit parameters and bounded scope.
82	4) Verify results and save output/evidence files.
83
84	## References
85
86	- `references/sources.md`

People who liked this also viewed

6 picks

Type