qwencloud-image-generation

Name: qwencloud-image-generation
Author: QwenCloud

32stars0forks

How to install qwencloud-image-generation?

qwencloud/qwencloud-ai/qwencloud-image-generation

$npx -y skills add QwenCloud/qwencloud-ai --skill qwencloud-image-generation

Installs into the current project.

Summary

[QwenCloud] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs

Files · 1

View on GitHub

SKILL.md

1	> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code),
2	> see [agent-compatibility.md](references/agent-compatibility.md) once per session.
3
4	# Qwen Image Generation
5
6	Generate and edit images using Wan and Qwen Image models. Supports text-to-image, reference-image editing (style
7	transfer, subject consistency, multi-image composition, text rendering), and interleaved text-image output.
8	This skill is part of qwencloud/qwencloud-ai.
9
10	## Skill directory
11
12	Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.
13
14	\| Location \| Purpose \|
15	\|----------\|---------\|
16	\| `scripts/image.py` \| Default execution — sync/async, upload, download \|
17	\| `references/execution-guide.md` \| Fallback: curl (sync/async), code generation \|
18	\| `references/prompt-guide.md` \| Prompt formulas, style keywords, negative_prompt, prompt_extend decision \|
19	\| `references/api-guide.md` \| API supplement \|
20	\| `references/sources.md` \| Official documentation URLs \|
21	\| `references/agent-compatibility.md` \| Agent self-check: register skills in project config for agents that don't auto-load \|
22
23	## Security
24
25	NEVER output any API key or credential in plaintext. Always use variable references (`$DASHSCOPE_API_KEY` in shell, `os.environ["DASHSCOPE_API_KEY"]` in Python). Any check or detection of credentials must be non-plaintext: report only status (e.g. "set" / "not set", "valid" / "invalid"), never the value. Never display contents of `.env` or config files that may contain secrets.
26
27	When the API key is not configured, NEVER ask the user to provide it directly. Instead, help create a `.env` file with a placeholder (`DASHSCOPE_API_KEY=sk-your-key-here`) and instruct the user to replace it with their actual key from the [QwenCloud Console](https://home.qwencloud.com/api-keys). Only write the actual key value if the user explicitly requests it.
28
29	## Key Compatibility
30
31	Scripts require a standard QwenCloud API key (`sk-...`). Coding Plan keys (`sk-sp-...`) cannot be used — image generation models are not available on Coding Plan, and Coding Plan does not support the native QwenCloud API. The script detects `sk-sp-` keys at startup and prints a warning. If qwencloud-ops-auth is installed, see its `references/codingplan.md` for full details.
32
33	## Mode Selection Guide
34
35	\| User Want \| Mode \| Model \|
36	\|-----------\|------\|-------\|
37	\| Generate image from text only \| t2i \| `wan2.6-t2i` (default), or `wan2.7-image` / `wan2.7-image-pro` \|
38	\| Edit image / apply style transfer based on 1–4 reference images \| image-edit \| `wan2.7-image-pro` / `wan2.7-image` / `wan2.6-image` \|
39	\| Subject consistency: generate new images maintaining subject from references \| image-edit \| `wan2.7-image-pro` / `wan2.7-image` / `wan2.6-image` \|
40	\| Multi-image composition: combine style from one image, background from another \| image-edit \| `wan2.7-image-pro` / `wan2.7-image` / `wan2.6-image` \|
41	\| Single-image editing preserving subject consistency \| i2i \| `wan2.5-i2i-preview` \|
42	\| Multi-image fusion: place object from one image into another scene \| i2i \| `wan2.5-i2i-preview` \|
43	\| Interleaved text-image output (e.g., tutorials, step-by-step guides) \| interleave \| `wan2.6-image` \|
44	\| Fast text-to-image drafts \| t2i \| `wan2.2-t2i-flash` \|
45	\| Edit text within images, precise element manipulation \| image-edit \| `qwen-image-2.0-pro` \|
46	\| Multi-image fusion with realistic textures \| image-edit \| `qwen-image-2.0-pro` \|
47	\| Posters / complex Chinese+English text rendering \| t2i \| `qwen-image-2.0-pro` \|
48	\| Text-to-image with fixed aspect ratios (batch) \| t2i \| `qwen-image-plus` / `qwen-image-max` \|
49
50	## Model Selection
51
52	### Wan Series (default)
53
54	\| Model \| Use Case \|
55	\|-------\|----------\|
56	\| wan2.6-t2i \| Recommended for text-to-image — sync + async, best quality \|
57	\| wan2.7-image-pro \| Multi-function (4K support) — text-to-image, image editing (0–9 images), sequential multi-image, interactive editing (bbox), thinking mode, color palette. Max 4K fo

People who liked this also viewed

6 picks

Type

qwencloud-image-generation

32stars0forks

View on GitHub

How to install qwencloud-image-generation?

qwencloud/qwencloud-ai/qwencloud-image-generation

$npx -y skills add QwenCloud/qwencloud-ai --skill qwencloud-image-generation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code),
2	> see [agent-compatibility.md](references/agent-compatibility.md) once per session.
3
4	# Qwen Image Generation
5
6	Generate and edit images using Wan and Qwen Image models. Supports text-to-image, reference-image editing (style
7	transfer, subject consistency, multi-image composition, text rendering), and interleaved text-image output.
8	This skill is part of qwencloud/qwencloud-ai.
9
10	## Skill directory
11
12	Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.
13
14	\| Location \| Purpose \|
15	\|----------\|---------\|
16	\| `scripts/image.py` \| Default execution — sync/async, upload, download \|
17	\| `references/execution-guide.md` \| Fallback: curl (sync/async), code generation \|
18	\| `references/prompt-guide.md` \| Prompt formulas, style keywords, negative_prompt, prompt_extend decision \|
19	\| `references/api-guide.md` \| API supplement \|
20	\| `references/sources.md` \| Official documentation URLs \|
21	\| `references/agent-compatibility.md` \| Agent self-check: register skills in project config for agents that don't auto-load \|
22
23	## Security
24
25	NEVER output any API key or credential in plaintext. Always use variable references (`$DASHSCOPE_API_KEY` in shell, `os.environ["DASHSCOPE_API_KEY"]` in Python). Any check or detection of credentials must be non-plaintext: report only status (e.g. "set" / "not set", "valid" / "invalid"), never the value. Never display contents of `.env` or config files that may contain secrets.
26
27	When the API key is not configured, NEVER ask the user to provide it directly. Instead, help create a `.env` file with a placeholder (`DASHSCOPE_API_KEY=sk-your-key-here`) and instruct the user to replace it with their actual key from the [QwenCloud Console](https://home.qwencloud.com/api-keys). Only write the actual key value if the user explicitly requests it.
28
29	## Key Compatibility
30
31	Scripts require a standard QwenCloud API key (`sk-...`). Coding Plan keys (`sk-sp-...`) cannot be used — image generation models are not available on Coding Plan, and Coding Plan does not support the native QwenCloud API. The script detects `sk-sp-` keys at startup and prints a warning. If qwencloud-ops-auth is installed, see its `references/codingplan.md` for full details.
32
33	## Mode Selection Guide
34
35	\| User Want \| Mode \| Model \|
36	\|-----------\|------\|-------\|
37	\| Generate image from text only \| t2i \| `wan2.6-t2i` (default), or `wan2.7-image` / `wan2.7-image-pro` \|
38	\| Edit image / apply style transfer based on 1–4 reference images \| image-edit \| `wan2.7-image-pro` / `wan2.7-image` / `wan2.6-image` \|
39	\| Subject consistency: generate new images maintaining subject from references \| image-edit \| `wan2.7-image-pro` / `wan2.7-image` / `wan2.6-image` \|
40	\| Multi-image composition: combine style from one image, background from another \| image-edit \| `wan2.7-image-pro` / `wan2.7-image` / `wan2.6-image` \|
41	\| Single-image editing preserving subject consistency \| i2i \| `wan2.5-i2i-preview` \|
42	\| Multi-image fusion: place object from one image into another scene \| i2i \| `wan2.5-i2i-preview` \|
43	\| Interleaved text-image output (e.g., tutorials, step-by-step guides) \| interleave \| `wan2.6-image` \|
44	\| Fast text-to-image drafts \| t2i \| `wan2.2-t2i-flash` \|
45	\| Edit text within images, precise element manipulation \| image-edit \| `qwen-image-2.0-pro` \|
46	\| Multi-image fusion with realistic textures \| image-edit \| `qwen-image-2.0-pro` \|
47	\| Posters / complex Chinese+English text rendering \| t2i \| `qwen-image-2.0-pro` \|
48	\| Text-to-image with fixed aspect ratios (batch) \| t2i \| `qwen-image-plus` / `qwen-image-max` \|
49
50	## Model Selection
51
52	### Wan Series (default)
53
54	\| Model \| Use Case \|
55	\|-------\|----------\|
56	\| wan2.6-t2i \| Recommended for text-to-image — sync + async, best quality \|
57	\| wan2.7-image-pro \| Multi-function (4K support) — text-to-image, image editing (0–9 images), sequential multi-image, interactive editing (bbox), thinking mode, color palette. Max 4K fo

People who liked this also viewed

6 picks

Type