Flux Klein Inpaint Native Node Only — v1.0
This workflow was created based on a request from the YouTube comments, asking for a low-VRAM setup with inpainting support , similar to my earlier low-VRAM workflows.
Perfil de ejecución
- Acceso
- Flujo externo
- Estado
- Publicado
- Versión
- Klein Inpaint.json
- Fuente
- Civitai
- Actualizado
- 15 oct 2026
Descripción de la fuente
This workflow was created based on a request from the YouTube comments, asking for a low-VRAM setup with inpainting support , similar to my earlier low-VRAM workflows.
Overview
GGUF-based workflow designed to run on low VRAM systems
Supports Q4 and Q6 models
Uses FP8 mixed text encoder for efficiency
Can also run FP16 models if you have higher VRAM available
Workflow Design
Built using only core, native nodes
No missing nodes or external dependencies
Loads and runs as-is
Inpainting Examples
Adding sunglasses by masking the face area
Changing clothing by masking the torso and prompting a new outfit
Lighting and overall consistency are preserved across edits
Why This Workflow Exists
Simple to read and modify
Focused on practical image editing
Optimized for systems with limited resources
What you need
- Model files
- 16.9 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requisitos
Modelos
3- Encontrado
Checkpoint · 16.9 GB · Hugging Face · unsloth/FLUX.2-klein-9B-GGUF
- Archivo sin verificar
VAE · Hugging Face · Comfy-Org/flux2-dev
qwen_3_8b_fp8mixed.safetensors
No resueltoText encoder · Hugging Face · Comfy-Org/flux2-klein-9B
Paquetes de nodos
2comfyui-gguf
PosiblePaquete de nodos · Registry
- Encontrado
Paquete de nodos · Registry
Fuentes
1 fuente
Fuentes
1 fuenteExtractos de fuentes
1 extracto
Extractos de fuentes
1 extractoSource context: 1585 downloads · Type Workflows · Base model Flux.2 Klein 9B
