krea2

Krea 2, MiniMax & Klein 9B LoRA - LoKR Studio — train, profile, repair, and extract Krea 2, Flux 2 Klein 9B & MiniMax LoRAs & LoKRs

AI character studio for portable identity. Build multi model consistent characters, train LoRAs, and generate on your own GPU.

Real-time multimodal AI pipelines on Apple Silicon

Advanced Seed Diversity, Conditioning Enhancement and Step Control node for ComfyUI

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.

Native ComfyUI nodes for Krea 2 AnyPaint - arbitrary-mask inpainting, outpainting, and mixed image editing.

514 Krea 2 Turbo prompts with generated examples and ComfyUI wildcards

中文 9 段式人像提示词创作体系 · 可直接出图的模板/风格预设/千条级批量生成器 · 覆盖全身照与上半身中景照 · 适配 ComfyUI/Krea2/GPT Image 2 · 无强制约束，创作自由

Prompt-only Krea moodboard search and style nodes for ComfyUI.

A ComfyUI diffusers implementation of Krea2 for the highest possible quality and most options

Model-aware sigma schedules, sampler compatibility validation, and versioned inference profiles for ComfyUI

Regional prompting + per-region LoRA for Krea 2 in ComfyUI — single-pass, canvas editor

ComfyUI custom nodes that guide Krea 2 with reference images: stack up to 12 guide cards using plain-language recipes - keep the subject, borrow style/palette/lighting/material, copy pose or shapes, avoid text/logos.

Run Krea 2 (Krea AI's 12B DiT) natively in Forge Neo — the first open-source Krea 2 extension. One-click model download, presets, fp8, full + piecewise loading. By Stable Yogi.

StormForge Krea2 Turbo LoRA Merger Suite

Prompt builder for Krea-2 in ComfyUI. Fill structured fields and get flowing prose in the format the model expects, not a keyword list.

Single-user training and generation platform on Modal. Train Krea 2 LoRAs, generate stills, and turn them into video with MiniMax-H3 (sound and picture in one pass) — one deploy, one URL, no infrastructure to keep alive.

Tooling for dataset captioning, model merging and quantizing.

Lightweight LOWVRAM optimised KREA2 webui

musubi-tuner GUI (Krea2 only)