krea

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

514 Krea 2 Turbo prompts with generated examples and ComfyUI wildcards

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

Krea 2 Turbo (12.9B text-to-image) ported to Apple MLX — local web UI + CLI, validated faithful to PyTorch

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.

MCP server for Krea.ai - Generate stunning AI images & videos with Flux, Hailuo, Runway, Kling, Ideogram, Imagen & more. Works with Claude Desktop, Claude Code, and any MCP client.

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.

Windows image-to-prompt app using local Ollama vision models

Fork of sd-forge-negpip: experimental Krea 2 prompt weighting / NegPiP for Forge Neo (personal, AI-assisted)

Browser extension that removes image censorship from krea realtime

The full Krea 2 Enhancement Suite for Forge Neo — advanced Prompt-Adherence engine + custom per-layer Detail Boost PRO. Free companion to sd-forge-krea2. By Stable Yogi.

Universal AI agent skill for generating images, videos, audio & music with 200+ local models via Wan2GP. Hardware-aware model selection, model-specific prompting, terminal image display. Works with Claude Code, Codex, Cursor, Gemini CLI & more.

Community Krea plugin for Codex with OAuth, image and video tools, LoRA support, and asynchronous job tracking on macOS.

Windows-first TagPilot fork with local LM Studio vision captioning, exact model discovery, one-image verification, and optional LAN access.

Cinematic local frontend for ComfyUI — MiniMax H3, Krea 2, Edit and video upscale. Seamless chunks, live preview, auto-connect to 127.0.0.1:8188.

A Python-based multi-GPU image generation pipeline using Huggingface Diffusers with LoRA (Low-Rank Adaptation) support. This project distributes image generation workloads across all available GPUs on the system leveraging Python multiprocessing to optimize throughput and speed.

KREA bu proje halen güncel yıllar geçmiş.

Run krea 2 turbo on mac

Per-token prompt weighting for Krea-2 in InvokeAI, accepting ComfyUI, A1111 and compel notation

Cuaderno de produccion abierto de las imagenes de Verso: el camino, los callejones sin salida y los prompts que salieron mal