nodes/Moeblack-ComfyUI-AnimaTool
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
33 Commits 3 Branches 0 Tags
dev
Commit Graph
33 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Nakano Kenji d720b8f927 docs: 完善 QwenEdit 双引擎支持的指南与声明 2026-02-19 00:59:56 +08:00
Nakano Kenji d5051313c1 docs(skills): 新增 skill 技能文档 2026-02-19 00:33:12 +08:00
Nakano Kenji e572748695 feat(mcp): 生图工具返回本地保存路径 
## 改动
- 在 \generate_anima_image\ 和 \generate_qwen_image\ 相关的响应中，附加图片在本地的绝对路径。

## 原因
方便大语言模型（如 QwenEdit）在多轮对话修图时，可以直接获取并引用上一轮生成的本地原图路径作为 \ase_image\。
 2026-02-18 23:41:01 +08:00
Nakano Kenji 6247d6b018 feat(qwen): 新增通义千问(Qwen)图像生成能力支持 
## 改动
- 新增 qwen_executor.py 与对应模板
- mcp_server 增加 generate_qwen_image 接口
- 更新依赖(uv.lock/pyproject.toml)
 2026-02-18 23:36:59 +08:00
Nakano Kenji 2a9c5fcbbb docs: add uvx installation guide 2026-02-08 14:27:38 +08:00
Nakano Kenji 47987534e9 enhance: improve tool descriptions and history robustness 
- mcp_server: add explicit required/optional markers to all tool params, improve reroll schema to auto-convert required to optional-override, update default neg prompt

- history: fix next_id to scan global max across all records, add file fallback search when record not found in memory
 2026-02-07 06:26:00 +08:00
Nakano Kenji f96700c1be license: change from MIT to AGPL-3.0 2026-02-07 04:22:10 +08:00
Nakano Kenji 27cc840be0 docs: update README - SillyTavern plugins released, add cross-references 2026-02-07 03:36:35 +08:00
Nakano Kenji db376a6936 docs: 酒馆 MCP 客户端添加 GitHub 链接 2026-02-06 19:24:06 +08:00
Nakano Kenji 92ccddb634 docs: 添加今日更新公告（十连抽/更换卡池/寻访记录） 2026-02-06 19:23:33 +08:00
Nakano Kenji b71aa81721 refactor(schema): 精简 TOOL_SCHEMA description，详细规则移至 Skill/Wiki 
- artist/loras/models 描述大幅精简，只保留最小必要信息

- CURSOR_SKILL: 补充画师格式规则、LoRA 技术细节、reroll/批量/模型切换

- wiki/Prompt-Guide: 补充画师格式规则、LoRA 技术细节、reroll 与批量生成

- 新增 unet_name/clip_name/vae_name 可选参数暴露模型切换能力
 2026-02-06 18:33:35 +08:00
Nakano Kenji c743ef5981 docs: 更新文档覆盖 reroll/history/repeat/batch_size 新功能 
- README: Features、Parameters 表、HTTP 路由表、目录结构

- wiki/API-Reference: 新增 list_anima_history/reroll_anima_image/list_anima_models 文档

- wiki/Home: Features 列表补充

- wiki/FAQ: 更新批量生成答案，新增 reroll FAQ

- mcp_server: generate/reroll 响应追加历史 ID 提示

- anima_executor: generate 返回 history_id 字段
 2026-02-06 18:25:27 +08:00
Nakano Kenji a94afd0818 feat(reroll): 新增生成历史记录系统和 reroll/history MCP 工具 
- 新增 executor/history.py：HistoryManager（内存 deque + JSONL 持久化）

- generate 完成后自动记录历史（参数、seed、尺寸等）

- 新增 MCP 工具 list_anima_history 和 reroll_anima_image

- generate 和 reroll 均支持 repeat（多次 queue）和 batch_size

- HTTP server 新增 /history 和 /reroll 端点
 2026-02-06 17:57:31 +08:00
Nakano Kenji 928b6512f6 Merge branch 'main' of https://github.com/Moeblack/ComfyUI-AnimaTool 2026-02-06 12:01:38 +08:00
Nakano Kenji 6eb5fecd37 fix(tools): 修改了工具介绍 2026-02-06 12:01:34 +08:00
Nakano Kenji 03c63836b4 docs: update Cherry Studio support status with preview release 2026-02-06 03:34:06 +08:00
Nakano Kenji 200ac420a1 Update README with Cherry Studio warning 
Added a note about Cherry Studio's MCP client limitations and a pending PR.
 2026-02-06 02:48:01 +08:00
Nakano Kenji bbf07c4f5b docs: add Related Projects section with AnimaLoraToolkit and example LoRA 2026-02-05 16:25:46 +08:00
Nakano Kenji 7b6b6d51eb fix(lora): normalize path separator to forward slash in list_models 2026-02-05 12:49:45 +08:00
Nakano Kenji b240bc1318 fix(lora): clarify and normalize lora_name matching 2026-02-04 18:34:13 +08:00
Nakano Kenji 020c25c5ff docs: add warning about Cherry Studio incompatibility 2026-02-04 10:05:16 +08:00
Nakano Kenji c1e68d8fcc Move nltags to end of prompt order (after environment) 
nltags is meant for 'last resort natural language description', so it makes sense to put it at the very end after all tags including environment.
 2026-02-04 03:42:44 +08:00
Nakano Kenji 7461fb1d0b docs: add style rules to hard rules in CURSOR_SKILL 2026-02-04 01:37:46 +08:00
Nakano Kenji b0d5566110 Add hero image to README for better first impression 2026-02-04 01:32:19 +08:00
Nakano Kenji c1c2e3dc0d Add parallel call support note to tool descriptions 2026-02-04 01:30:49 +08:00
Nakano Kenji 59f8752c8c docs: add CURSOR_SKILL.md and update README links 2026-02-04 01:08:35 +08:00
Nakano Kenji a9039ee4f8 feat: add model pre-check and model path configuration 
Model configuration:

- Add COMFYUI_MODELS_DIR for model pre-check (optional)

- Add ANIMATOOL_UNET_NAME, ANIMATOOL_CLIP_NAME, ANIMATOOL_VAE_NAME

- Add ANIMATOOL_CHECK_MODELS toggle

Model pre-check:

- Check if model files exist before generation

- Friendly error message with download link

- Skipped when COMFYUI_MODELS_DIR not set (remote ComfyUI)

Other improvements:

- Use config model names as defaults in _inject()

- Export DEFAULT_*_NAME constants
 2026-02-03 21:32:07 +08:00
Nakano Kenji f7fd0c07d9 feat: add environment variable configuration and improve error handling 
Configuration improvements:

- Support COMFYUI_URL environment variable for remote/Docker ComfyUI

- Add ANIMATOOL_TIMEOUT, ANIMATOOL_DOWNLOAD_IMAGES, etc.

- Can configure via MCP env block without modifying code

Error handling improvements:

- Add check_comfyui_health() for friendly connection error messages

- Better error messages when ComfyUI is not running

- Detect and report ComfyUI execution errors

Documentation:

- Add environment variable reference table to README

- Add remote/Docker ComfyUI configuration guide

- Expand troubleshooting section with common issues

- Add system requirements section
 2026-02-03 21:29:28 +08:00
Nakano Kenji d31d284ad5 fix: change round_to default from 8 to 16 for Cosmos spatial_patch_size compatibility 
Anima model (based on Cosmos architecture) requires latent space dimensions to be divisible by spatial_patch_size=2. Since VAE scales down by 8x, pixel dimensions must be divisible by 8*2=16.

Changes:

- Update round_to default from 8 to 16 in config.py and anima_executor.py

- Add align_dimension() function to align user-provided width/height

- Apply alignment to directly specified width/height (not just aspect_ratio)

- Update schema descriptions to document 16-multiple requirement
 2026-02-03 21:24:27 +08:00
Nakano Kenji b8682d9b5d Clarify multi-artist support: works but less stable, AI should prefer single artist 2026-02-03 17:12:39 +08:00
Nakano Kenji 0fe16ff866 Merge remote LICENSE 2026-02-03 16:19:26 +08:00
Nakano Kenji 7917b066f2 Initial release v1.0.0 
- MCP Server: Native image display in Cursor/Claude
- ComfyUI HTTP API: /anima/health, /anima/schema, /anima/knowledge, /anima/generate
- Standalone FastAPI server and CLI tool
- Structured prompt system with 14 aspect ratio presets
- Expert knowledge base for Anima prompting
 2026-02-03 16:18:57 +08:00
Nakano Kenji 4e41e2d970 Initial commit 2026-02-03 16:18:31 +08:00