Krea2 workflow | ti2i 16GB VRAM CivitAI metadata, upscaling, controlnet, FaceDetailer (+indexing elements), inpainting ComfyUI beginner friendly K2 — v2 — v6
Takes a bit more time for even more realism and correct posing.
Profil d'exécution
- Accès
- Flux de travail externe
- Statut
- Présenté
- Version
- blinksKrea2SimplePhoto_v6.json
- Source
- Civitai
- Mis à jour
- 1 oct. 2026
What you need
- Model files
- 20 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Exigences
Modèles
11- Trouvé
Object Detector · 49.6 MB · Hugging Face · Bingsu/adetailer
depth-control-lora.safetensors
Non résoluControlNet · Unknown
ema_vae_fp16.safetensors
Non résoluVAE · Unknown
- Trouvé
Checkpoint · 9.86 GB · Hugging Face · vantagewithai/Krea-2-Raw-GGUF
LoRA · 26.4 MB · SAFETENSOR · bf16 · Hugging Face · Kutches/Kr3a
krea2_turbo-Q4_K_M.gguf
Non résoluCheckpoint · Unknown
VAE · 242 MB · SAFETENSORS · fp8 · pruned · Civitai · 2641326
Text encoder · 4.50 GB · Hugging Face · ethanfel/Qwen3-VL-4B-Heretic-ComfyUI-ConvRot-INT8
Text encoder · 4.88 GB · SAFETENSORS · Civitai · 2753756
seedvr2_ema_7b-Q4_K_M.gguf
Non résoluCheckpoint · Unknown
VAE · 484 MB · Hugging Face · Kijai/WanVideo_comfy
Packs de nœuds
7ComfyUI_Comfyroll_CustomNodes
TrouvéPack de nœud · Registry
comfyui_controlnet_aux
PossiblePack de nœud · Registry
comfyui-custom-scripts
TrouvéPack de nœud · Registry
comfyui-image-saver
TrouvéPack de nœud · Registry
comfyui-impact-pack
TrouvéPack de nœud · Registry
comfyui-inpaint-cropandstitch
TrouvéPack de nœud · Registry
rgthree-comfy
TrouvéPack de nœud · Registry
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
Use this Krea 2 v6 ComfyUI workflow to create images from prompts or loaded images, then preview or save them; it also includes paths for ControlNet, inpainting, face detailing, and upscaling.
Flux
The graph includes Krea2 control, crop-and-stitch inpainting, face-detailing, and SeedVR2 upscaling nodes.
Entrées et sorties
Prompt text and loaded images enter through `CLIPTextEncode` and `LoadImage`; `PreviewImage` and `Image Saver` provide preview and save outputs.
Installation
Setup calls for a diffusion model, text encoder, VAE, and Turbo LoRA.
To use ControlNet, the instructions say to clone `comfyui-krea2-controlnet` into `custom_nodes` and get the linked depth-control LoRA.
Dépendances
ComfyUI node packages named for this workflow: `ComfyUI_Comfyroll_CustomNodes`, `comfyui_controlnet_aux`, `comfyui-custom-scripts`, `comfyui-image-saver`, `comfyui-impact-pack`, `comfyui-inpaint-cropandstitch`, and `rgthree-comfy`.
Named model files include `bbox/face_yolov8m.pt`, `depth-control-lora.safetensors`, `ema_vae_fp16.safetensors`, `krea2_raw-Q6_K.gguf`, `Krea2_TextFusion_Refusal_Reduction.safetensors`, and `krea2_turbo-Q4_K_M.gguf`.
Other named model files are `qwen_image_vae.safetensors`, `qwen3-vl-4b-heretic_int8_dynamic_convrot.safetensors`, `qwen3vl_4b_fp8_scaled.safetensors`, `seedvr2_ema_7b-Q4_K_M.gguf`, and `Wan2_1_VAE_fp32.safetensors`.
Configuration
Ollama generation and options nodes are included; the instructions name `gemma-4-12B-it-uncensored-heretic.Q8_0.gguf` for Ollama.
Précautions
Confirm where to get `ema_vae_fp16.safetensors`, `krea2_turbo-Q4_K_M.gguf`, and `seedvr2_ema_7b-Q4_K_M.gguf` before setup; no download URLs are listed for them.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 source
Sources
1 sourceExtraits de sources
1 extrait
Extraits de sources
1 extraitSource context: 1540 downloads · Type Workflows · Base model Krea 2
