Login
agents365-ai/365-skills12 files

Imagencn

Multi-platform AI image generation via DashScope/Ark/Hunyuan/Zhipu/StepFun plus Grok/OpenAI/Gemini/FLUX (international), specializing in Chinese text rendering and photorealistic images

Use this skillView repositoryView on skills.sh
Specification
Skill ID
agents365-ai/365-skills/imagencn
Publisher
agents365-ai
Repository
365-skills
Installs
0
Files
12
Synced
Sep 23, 2026
How to use it

Open any RiverX project, open the Skills panel in the chat, and search for this identifier. The files are fetched from the source repository at install time.

agents365-ai/365-skills/imagencnInstalls these files
  • SKILL.md
  • scripts/bfl.py
  • scripts/gemini.py
  • scripts/generate_image.py
  • scripts/grok.py
  • scripts/hunyuan.py
  • scripts/openai_img.py
  • scripts/providers/__init__.py
  • scripts/providers/base.py
  • scripts/stepfun.py
  • scripts/volcano_ark.py
  • scripts/zhipu.py

What this skill tells the agent

imagencn - Multi-Cloud Text-to-Image Skill

Overview

imagencn — Image Generation, Cloud-Native: one CLI, every image cloud. The project started with China-friendly clouds and now covers international providers as well.

Generate images using Alibaba Cloud Bailian API. Default endpoint is China region.

Supports nine platforms across fourteen model families:

  • Alibaba Cloud Bailian (DashScope): Qwen-Image 2.0, Qwen-Image Edit, Qwen-Image legacy, Wan Series, Z-Image
  • ByteDance Volcano Ark: Doubao-Seedream series (OpenAI-compatible REST)
  • Tencent Hunyuan: Hunyuan Image 3.0 (OpenAI-compatible REST)
  • Zhipu / BigModel: CogView-4 and GLM-Image (OpenAI-compatible REST)
  • StepFun / 阶跃星辰: Step-2X and Step-Image-Edit (OpenAI-compatible REST)
  • Google Gemini (international): Gemini 3 Pro Image / 3.1 Flash Image (generateContent REST)
  • Grok / xAI (international): Grok Imagine (OpenAI-compatible REST)
  • OpenAI (international): GPT Image 1 / 2 (Images API)
  • Black Forest Labs / FLUX (international): FLUX.2 Pro / Max (async REST)

Cross-platform support: Windows, macOS, Linux

When to Use This Skill

Automatically activate this skill when:

  • User requests image generation with Chinese text or calligraphy
  • Need photorealistic images or photography-style visuals
  • Creating commercial posters, illustrations, or digital art
  • User mentions any of these: Alibaba Cloud / Bailian / Qwen / Wan / DashScope, ByteDance / Volcano Ark / Seedream / Doubao, Tencent / Hunyuan, Google / Gemini / Nano Banana, Grok / xAI, OpenAI / GPT Image, FLUX / Black Forest Labs
  • User wants an international (non-China) image provider — use the Gemini / Grok / OpenAI / FLUX platforms
  • Any task where AI-generated image with strong Chinese support would be helpful

Model Reference

When the user wants to compare models, check pricing, or browse options before choosing, open the local model reference page in their browser:

open ~/.claude/skills/imagencn/docs/models.html

This page shows all 44 models across 9 platforms with pricing, resolution, feature highlights, and a quick-reference guide. On Linux use xdg-open; the file also works from file:// with no server needed.

Workflow

Step 1 — Refine the prompt (interactive, never skip)

Users often give short, casual descriptions ("生成一只猫"). Before calling the API, present 3 refined prompt options with different style directions. Add, as appropriate:

  • Subject details (shape, colour, material, expression, pose)
  • Lighting (golden hour, studio, rim light, soft diffused, neon, cinematic)
  • Composition (rule of thirds, shallow depth of field, wide shot, close-up)
  • Style / medium (photorealistic, oil painting, watercolour, 3D render, vector)
  • Mood / atmosphere (serene, dramatic, whimsical, dystopian, elegant)
  • Quality keywords (8K, hyperdetailed, award-winning, professional photography)
  • For Chinese text on images: text content, placement, font style, colour, size

Label the options clearly (e.g. A / B / C) with a one-line summary of each direction. Let the user pick one, combine elements from multiple, or request a new direction. Iterate until they confirm ("go", "generate", "ok", etc.), then proceed to generation.

Step 2 — Pick a model

Choose based on the request (see Model Selection Guide below). Default to qwen-image-2.0-pro if unsure. Mention your choice to the user.

Step 3 — Pick a size

Native 2K for Qwen-Image 2.0, 1K/2K/4K for Wan2.7, or an aspect-ratio preset (16:9, 1:1, etc.).

Step 4 — Generate

Run scripts/generate_image.py with the confirmed prompt and output path.

Step 5 — Save

If the output path was implicit, save into the user's current working directory.

Models

Qwen-Image 2.0 family - Latest Flagship (MultiModalConversation API)

ModelDescription
qwen-image-2.0-proDefault. Latest flagship, native 2K, strongest typography and detail
qwen-image-2.0-pro-2026-06-22Latest snapshot (Jun 2026): generation + editing fusion, better text rendering and prompt adherence
qwen-image-2.0Standard 2.0 tier, native 2K
qwen-image-maxPrevious-gen flagship (Dec 2025)
qwen-image-max-2025-12-30qwen-image-max snapshot: improved realism, fewer AI artifacts

Qwen-Image Edit family - Image Editing (MultiModalConversation API)

Editing models require an input image via --image (local path or URL). Omit --size to match the input image dimensions.

ModelDescription
qwen-image-edit-maxFlagship editing model, strongest instruction following
qwen-image-edit-max-2026-01-16Latest max snapshot (Jan 2026)
qwen-image-edit-plusFaster, lower-cost editing

Qwen-Image legacy (ImageSynthesis API)

ModelDescription
qwen-image-plusDistilled accelerated version of qwen-image-max
qwen-image-plus-2026-01-09qwen-image-plus snapshot (Jan 2026): faster high-quality generation
qwen-imageBase model

Wan Series - Photorealistic Generation (ImageGeneration API)

ModelDescription
wan2.7-image-proLatest. Up to 4K output, unified architecture (T2I + edit + multi-image)
wan2.7-imageWan 2.7 standard, up to 2K
wan2.6-t2iWan 2.6, flexible sizing
wan2.5-t2i-previewHigh quality, up to 768x2700
wan2.2-t2i-flashSpeed-optimized
wan2.2-t2i-plusProfessional tier
wanx2.1-t2i-turboFast execution
wanx2.1-t2i-plusProfessional tier
wanx2.0-t2i-turboEarlier generation

Z-Image - Lightweight & Fast (MultiModalConversation API)

ModelDescription
z-image-turboFast, low-cost generation; bilingual (CN/EN) text rendering, high-fidelity portraits and product images. Pixel area 512x512 to 2048x2048

Volcano Ark - ByteDance Seedream (OpenAI-compatible API)

ModelDescription
doubao-seedream-5-0-260128Ark default. Latest, up to 3K, PNG/JPEG output, best text rendering
doubao-seedream-4-5-251128Seedream 4.5, up to 4K
doubao-seedream-4-0-250828Seedream 4.0, up to 4K, budget-friendly

Tencent Hunyuan (OpenAI-compatible API)

ModelDescription
hy-image-v3.0Hunyuan default. Flagship 3.0, strong composition awareness, handles complex Chinese prompts up to 8K chars

Zhipu / BigModel - CogView-4 & GLM-Image (OpenAI-compatible API)

ModelDescription
cogview-4Zhipu default. Stable alias for latest CogView-4, native Chinese text rendering
cogview-4-250304CogView-4 fixed snapshot (Mar 2025), reproducible results
glm-imageGLM-Image flagship, up to 2048x2048, hybrid autoregressive/diffusion

StepFun / 阶跃星辰 - Step-2X (OpenAI-compatible API)

ModelDescription
step-2x-largeStepFun default. High quality (0.1 RMB/image), up to 1024x1024
step-image-edit-2Fast & cheap (0.02 RMB/image), supports negative prompts, 8 inference steps

Google Gemini - International (generateContent API)

ModelDescription
gemini-3-pro-image-previewGemini default. Google flagship image model, 512/1K/2K named sizes plus aspect-ratio presets
gemini-3-pro-imageStable flagship (Nano Banana Pro), 1K/2K/4K
gemini-3.1-flash-imageNano Banana 2: fast generalist, 512/1K/2K/4K, strong text rendering
gemini-3.1-flash-lite-imageNano Banana 2 Lite: fastest/cheapest, 1K only

Grok / xAI - International (OpenAI-compatible API)

ModelDescription
grok-imagine-image-qualityGrok default. High-quality Grok image model, aspect-ratio + resolution presets (up to 4K)

More from agents365-ai

agents365-ai/365-skills

Agent Native Design

Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.

agents365-ai/365-skills

Asta Skill

Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.

agents365-ai/365-skills

Bangumi Frames

Extract and organize frames from a Bilibili video (bangumi episode, UP upload, or a local file) into scenery shots and per-character image groups, using anime-specific person detection + CCIP character-identity embeddings. Two modes — cluster everyone, or pull out one (or several) named characters via reference folders. Use when the user wants to collect, extract, or organize anime frames/screenshots by character or by scenery from a Bilibili video. Read-only download for personal viewing/analysis; uploads nothing.

Use this skill in a project

Open any RiverX project, search the Skills panel for agents365-ai/365-skills/imagencn, and install it in one click.

Use this skill