Krea2 Turbo Workflow + Upscale + Reference + Editing + Uncensored — v2.1 — v2.6
DonutNodes now runs about 70-100% faster when using lora's (also than standard lora loading) on lesser vram cards (12gb and below). Remember to update. also changes to how lora's are applied when txtfusion layers are...
Laufzeitprofil
- Zugriff
- Externer Arbeitsablauf
- Status
- Aufgelistet
- Version
- DonutWF-Krea2-2_6_.json
- Quelle
- Civitai
- Aktualisiert
- 4. Nov. 2026
Quellenbeschreibung
DonutNodes now runs about 70-100% faster when using lora's (also than standard lora loading) on lesser vram cards (12gb and below). Remember to update. also changes to how lora's are applied when txtfusion layers are uncensored. Depending on what you want to do, it might make sense disabling the LoRA's as fineporn base model is very good at nsfw on it's own when the uncensoring is applied, which it is by default. the loras are applied for style and realism, not capability.
What you need
- Model files
- 6.6 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Anforderungen
Modelle
104x_NickelbackFS_72000_G.pth
Nicht aufgelöstUpscaler · Unknown
face_yolov8m.pt
Nicht aufgelöstObject Detector · Unknown
- Nicht aufgelöst
Diffusion model · Unknown
Krea2_HMNSFW_AIO.safetensors
Nicht aufgelöstCheckpoint · Unknown
LoRA · 1.70 GB · SAFETENSORS · FP16 (tensor header) · Unknown
Krea2_NSFW_Aesthetics_V1.safetensors
Nicht aufgelöstCheckpoint · Unknown
qwen_image_vae.safetensors
MöglichVAE · Unknown
Text encoder · 4.88 GB · SAFETENSORS · U8 + FP32 + BF16 + FP8 (tensor header) · Unknown
realism_engine_krea2_v1.safetensors
Nicht aufgelöstCheckpoint · Unknown
sam_vit_b_01ec64.pth
Repository zugeordnetSegmentation · Unknown
Knotenpakete
14cg-use-everywhere
GefundenKnotenpaket · Registry
ComfyUI_Comfyroll_CustomNodes
GefundenKnotenpaket · Registry
comfyui_essentials
GefundenOptionalKnotenpaket · Registry
ComfyUI-bleh
GefundenKnotenpaket · Registry
comfyui-impact-pack
GefundenKnotenpaket · Registry
- Gefunden
Knotenpaket · GitHub · ltdrdata/ComfyUI-Impact-Subpack
derfuu_comfyui_moddednodes
GefundenKnotenpaket · Registry
donutnodes
Nicht aufgelöstKnotenpaket · Registry
Fast Groups Bypasser (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
krea2-nag
Nicht aufgelöstKnotenpaket · Registry
mikey_nodes
GefundenKnotenpaket · Registry
RES4LYF
GefundenKnotenpaket · Registry
rgthree-comfy
GefundenKnotenpaket · Registry
was-node-suite-comfyui
MöglichKnotenpaket · Registry
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Zweck
The Krea 2 Donut workflow is for creating and refining images: it generates from a prompt and can edit, inpaint, or outpaint using a base image and optional second reference; it takes a prompt and resolution and provides image previews and saved images.
Fluss
For inpainting or outpainting, paint or draw a selection, invert it, adjust overlap and seam width, or expand the canvas with directional presets; outpainting stays within the megapixel budget.
Finishing can include first and second upscales, Face Detailer, and SeedVR2, with an individual preview for each stage.
Eingaben und Ausgaben
The supplied preset saves to output/Final with seed-based filenames and supports PNG or WebP workflow metadata.
Einrichtung
Install DonutNodes 3.0.23+, restart ComfyUI, refresh the browser, open DonutWF_v5.json, then use Manager → Install Missing Nodes and restart again.
For model downloads, the description lists GitHub’s Download missing option or the Registry/Manager DonutNodes-model-installer.zip; some downloads may require an access token.
Abhängigkeiten
The workflow lists these node packs: cg-use-everywhere, ComfyUI_Comfyroll_CustomNodes, comfyui_essentials, ComfyUI-bleh, comfyui-impact-pack, comfyui-impact-subpack, derfuu_comfyui_moddednodes, and donutnodes.
It also lists krea2-nag, mikey_nodes, RES4LYF, rgthree-comfy, and was-node-suite-comfyui.
Model files named for the workflow include 4x_NickelbackFS_72000_G.pth, bbox/face_yolov8m.pt, finepornV4INT8NVFP4BF16_v4.safetensors, Krea2_HMNSFW_AIO.safetensors, krea2/krea2_identity_edit_v1_2.safetensors, krea2/Krea2_NSFW_Aesthetics_V1.safetensors, qwen-image/qwen_image_vae.s:
Konfiguration
For a first text-to-image run, leave Editing off; to edit, enable it, add the base image to A, optionally add a second image to B, and describe the change in the prompt.
Vorschlag · nicht geprüft
For reference B, choose Prompt selection to mask a named object or Auto subject for the foreground; separate reference guidance pauses while Editing is enabled.
You can add, duplicate, and reorder prompt variants, keep one active or cycle through them automatically, and adjust LoRA strengths and block weights.
Vorsichtsmaßnahmen
High-resolution editing with multiple references and NAG can be VRAM-heavy; seam quality depends on the image, prompt, and overlap settings.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 Quelle
Quellen
1 QuelleWorkflow instructions
Author notes from DonutWF-Krea2-2_6_.json · selected release
face_yolov8m.pt - URL: https://huggingface.co/Bingsu/adetailer/resolve/main/face_yolov8m.pt - Size: 52 MB - SHA256: 717923c19b3f4bbf5250b728f1fa6b2cb72a33aed1d236ea9caf0e21ad943e5f - Folder: ComfyUI/models/ultralytics/bbox/ nickelback → 4x_Nickelback_70000G.pth (ESRGAN upscaler) - URL: https://huggingface.co/licyk/sd-upscaler-models/resolve/3a2094a57f456c41b79e5a4d196f2222c9940b89/ESRGAN/4x_Nickelback_70000G.pth?download=true - Size: 67 MB - Folder: ComfyUI/models/upscale_models/ sam_vit_b_01ec64.pth - URL: https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth - Size: 375 MB - SHA256: ec2df62732614e57411cdcf32a23ffdf28910380d03139ee0f4fcbe91eb8c912 - Folder: ComfyUI/models/sams/ zImageClearVae_halfNatural.safetensors - URL: https://huggingface.co/easygoing0114/Z-Image_clear_vae/resolve/main/Z-Image_half_natural_vae.safetensors - Size: 335 MB - Folder: ComfyUI/models/vae/ - Note: HF filename is Z-Image_half_natural_vae.safetensors (underscores); the receiver would need to rename to zImageClearVae_halfNatural.safetensors to match the workflow reference, or we ship an alias. - Also has variants in the same repo: natural, clear, vivid.
Download files
Modellartefakte
2 Artefakte
Modellartefakte
2 ArtefakteQuellenauszüge
2 Auszüge
Quellenauszüge
2 AuszügeSource context: 33033 downloads · Type Workflows · Base model Krea 2
Source context: 31437 downloads · Type Workflows · Base model Krea 2
