novelai-workflowsNovelAI creative workflows for OpenClaw: fiction context, chapter planning, image prompting, V5/V4.5 generation, img2img, inpainting, Vibe/Director tools, cost-aware execution, same-session billing-profile reuse, bounded transient retries, and secret-safe asset records.
Install via ClawdBot CLI:
clawdbot install techotaku39/novelai-workflowsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains telemetry, tracking, or analytics calls not mentioned in documentation
pixel(Calls external URL not in known-safe list
https://github.com/techotaku39/openclaw-novelaiAudited Oct 2, 2026 · audit v1.0
Generated Oct 2, 2026
An indie author uses the skill's project_state.py helper to maintain canon, memory, lorebook, and style files across dozens of chapters, then composes bounded 30K-char context windows for the NovelAI text model. The outline, continue, rewrite, review, and summarize actions keep character consistency and continuity while the author focuses on creative decisions.
A small studio combines chapter writing with NovelAI image generation to produce consistent character art for each scene. They use V5 generation, Vibe/Director tools, and img2img for style matching, while the billing-profile reuse and Anlas cost estimation keep expenses predictable across a high-volume image workload.
A game master runs a persistent NovelAI project per campaign, using lorebook and memory files to track NPCs, factions, and plot threads. Session prep generates recaps, encounter descriptions, and NPC portraits, with inpainting used to fix or edit generated character tokens and scene maps.
A content agency uses the skill to draft branded long-form narratives, case study stories, and campaign lore for clients. They leverage the review action for editorial QA, summarize to distill client-approved canon, and image generation for accompanying hero visuals and social assets.
A community platform integrates the skill to let users write and illustrate branching stories with AI assistance. The session-scoped billing profile and secret-safe rules protect user accounts, while the bounded context scripts prevent runaway token costs and keep each user's canon isolated to their workspace.
Offer tiered monthly plans where writers and small teams get hosted novelai-projects, chapter context management, and a monthly Anlas/image credit allowance. Value is driven by persistent canon/lorebook storage and time saved on continuity maintenance rather than raw generation access.
Sell done-for-you illustrated chapter packages, character bibles, or campaign content bundles produced using the skill's workflow. Pricing is per deliverable or per word, with image assets and revision rounds included as defined scopes.
License the orchestration layer and project_state tooling to fiction platforms, game studios, or comic apps that want to embed AI-assisted writing and illustration. Integration includes compliance guardrails around credential handling and cost estimation for end users.
💬 Integration Tip
Always verify the active MCP tool catalog and schema before calling image tools, since namespacing and model support (e.g., Vibe limited to V4/V4.5) vary by host and the advertised upscale_image route has returned 404s. Use streaming for GLM-4.6 and confirm an output file exists before claiming any generation succeeded.
Scored Oct 2, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。