Basic Krea 2 Workflow
Important Update: The Fantastic Lora Loader is broken when using the latest version from the repository. Clone my fork of the repo here to fix it.
Profil d'exécution
- Accès
- Flux de travail externe
- Statut
- Présenté
- Version
- basicKrea2Workflow_t2i.json
- Source
- Civitai
- Mis à jour
- 3 nov. 2026
Description de la source
No release description captured.
What you need
Hardware and download-size estimates are not available yet.
Exigences
Modèles
4Krea2_Turbo_convrot_int8mixed.safetensors
Non résoluDiffusion model · Unknown
krea2_turbo_lora_rank_64_bf16.safetensors
Non résoluOptionnelLoRA · Unknown
qwen3VLInstruct4bHeretic_int8Convrot.safetensors
Non résoluText encoder · Unknown
Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors
Non résoluVAE · Unknown
Packs de nœuds
9Pack de nœud · GitHub · blue-pen5805/ComfyUI-krea2-negpip
comfyui-fantastic-loras
TrouvéPack de nœud · Registry
- Trouvé
Pack de nœud · Registry
comfyui-logic
TrouvéPack de nœud · Registry
- Trouvé
Pack de nœud · GitHub · kijai/ComfyUI-KJNodes
Label (rgthree)
Non résoluPack de nœud · Unknown
Node Bypasser
Non résoluPack de nœud · Unknown
rgthree-comfy
TrouvéPack de nœud · Registry
Pack de nœud · GitHub · spacepxl/ComfyUI-VAE-Utils
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
Objectif
Basic Krea 2 Workflow is for starting Krea 2 workflows. It takes prompt text, can optionally enhance prompts with Krea’s own text encoder, and can stack LoRAs; its output format is not specified.
Entrées et sorties
Prompt text is used with the optional enhancer, while the workflow’s output format is not specified.
Installation
The listed version is Basic Krea 2 Workflow, published by Pixllvr941, and uses Krea 2 as its base model.
Dépendances
The workflow lists four node packs: comfyui-fantastic-loras, comfyui-kjnodes, comfyui-logic, and rgthree-comfy.
It lists these required model files: Krea2_Turbo_convrot_int8mixed.safetensors and krea2_turbo_lora_rank_64_bf16.safetensors.
It also lists qwen3VLInstruct4bHeretic_int8Convrot.safetensors and Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors.
Configuration
Settings are described as easy to find, and the optional prompt enhancer uses Krea’s own text encoder.
The Fantastic Lora Loader stacks LoRAs, and versions are available with and without Face Fix.
Précautions
Before using the workflow, verify that all four listed model files are available in your setup.
Suggestion · non vérifié
If Comfy does not start, check whether your setup needs a manual huggingface-hub upgrade from 0.24.0 to 0.34.0; the description reports this for one setup and does not say whether it is common.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 source
Sources
1 sourceWorkflow instructions
Author notes from basicKrea2Workflow_t2i.json · selected release
# 📁 Downloads links for the text encoder and vae I use (recommended) **Text Encoder:** 👉 [qwen3VLInstruct4bHeretic_int8Convrot.safetensors](https://civitai.red/api/download/models/3099765?fileId=2979509) **VAE:** 👉 [Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors](https://huggingface.co/spacepxl/Wan2.1-VAE-upscale2x/resolve/main/Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors?download=true)
Author notes from basicKrea2Workflow_t2i.json · selected release
# 🖼️ Krea 2 Quantized — ComfyUI Quick Setup All quantized models (FP8 / MXFP8 / NVFP4 / INT8 / ConvRot INT8) for both Base and Turbo: 👉 **[Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8](https://huggingface.co/Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8)** --- ## Required Downloads **Text Encoder** — Comfy now supports INT8 text encoders! Load with CLIPLoader, type `krea2`: 👉 [qwen3vl_4b_INT8.safetensors](https://huggingface.co/Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8/resolve/main/Text%20Encoder/qwen3vl_4b_int8.safetensors) **VAE** — Same as Anima: 👉 [qwen_image_vae.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/vae/qwen_image_vae.safetensors) --- ## Recommended Settings | Model | Steps | CFG | Resolution | |-------|-------|-----|------------| | Turbo | 8 | 0.0 | 1024–2048px | | Raw | 52 | 3.5 | up to 1024px |
Download files
Artefacts du modèle
2 artefacts
Artefacts du modèle
2 artefactsExtraits de sources
3 extraits
Extraits de sources
3 extraitsSource context: 1239 downloads · Type Workflows · Base model Krea 2
Source context: 844 downloads · Type Workflows · Base model Krea 2
Source context: 326 downloads · Type Workflows · Base model Krea 2
