anima

Reference-image character and style transfer for Anima in ComfyUI (offset-RoPE reference frame + LoRA)

Train LoRAs for Qwen-Image 2.1, FLUX.2 Klein 9B, FLUX.3 Image Klein, Krea 2, Z-Image, MOSS-Image, ERNIE-Image, Ideogram 4, Anima, SDXL (Pony, Illustrious, NoobAI), LTX 2.3, MiniMax-H3, and more on NVIDIA GPUs from 4–8 GB VRAM. One install, one launcher, NF4 models. Windows, Linux and RunPod.

Anima LoRA Factory is a user-friendly GUI tool designed for training LoRAs for the next-generation Anima diffusion models.

A better ComfyUI sampler for Anima — Cosmos-style RF sampling (FlowUniPC + PC3, RF linear shift) for stronger prompt adherence, structure, and detail retention.

Low VRAM SDXL Fine-Tuning Toolkit 2026: Train Full-Quality AI Models on 12GB GPUs

The 2026 VRAM-Smart Fine-Tuning Suite for SDXL and ANIMA on 12GB GPUs

Apply 28-block Anima LoRAs to Anima-2.9B (40 blocks) with the correct block-index mapping, at load time and without converting files

ComfyUI 自定义节点：ANIMA3 提示词随机生成器 · 五级 NSFW 档位闸门 · 三层权重 · 角色库 2383 位 + 场景搭配 261 条 · 纯本地零依赖 · 只生成提示词，不生成图片

Light module to help design websites with Nuxt.

TK Toolkit (formerly Anima Toolkit) — all-in-one Anima/SD toolkit for ComfyUI: LoRA manager (batch apply + Civitai metadata & downloads), Danbooru search & waterfall gallery, bilingual prompt cards with Chinese tag autocomplete, output gallery, and batch-workflow utilities.

A highly memory-efficient fine-tuning toolkit for SDXL and ANIMA, combining modern VRAM-saving techniques with custom optimizers to enable full-quality model training on GPUs with as little as 12 GB of VRAM.

ComfyUI 自定义节点：ANIMA3 提示词随机生成器（V5）· 五级 NSFW 档位闸门 + 三层权重 · 2390 角色 / 271 场景搭配 · 纯本地 · 零依赖 · 运行时零联网 · 只生成提示词，不生成图片

Pick a post from Danbooru, Gelbooru, e621 and more, and copy a clean prompt for Illustrious, Pony, SDXL or Anima.

Use LoRAs, model merges and ControlNets (LLLite/VACE) across Anima generations (Anima, 2.9B, 3.8B/Pro52 and beyond) with automatic block-index remapping

Dragon Trainer（原 Anima LoRA WebUI / ALW）：Anima、Krea-2、Z-Image、Qwen-Image 2.1、MOSS-Image 的多模型训练与 WebUI 工作台

ComfyUI custom nodes: anime character styling console (clothing / pose / expression / scene slots) with a cross-plugin tag arbiter. Zero third-party dependencies.

Offline anime image generation on the Snapdragon 8 Gen 1 NPU (Hexagon V69), no root. Android app.

基于 ComfyUI 与 Anima Tools 的本机随机生图 WebUI：提示词池随机抽取、批量生成、LoRA 管理、多种高清修复、收藏树与风格预设，全部只连本机服务。Local random-generation workbench for ComfyUI + Anima Tools — prompt pools, batch generation, LoRA trigger words, hires-fix/Detailer, favorites tree, and style presets. Localhost-only.

ComfyUI nodes: turn a short idea into a checked Danbooru-tag prompt for the Anima model with a local LLM.

Bring a folder of images, leave with a trained LoRA. Agent skills (SKILL.md) for quality-gated LoRA training: dataset doctor + safe fixer + one-confirmation training orchestration for SD-Trainer / lora-scripts-next. Anima-first, SD1.5/SDXL/Flux.