🍩 Donut Workflow V5
Krea2 • DonutNodes 3.0.23+
Generate, edit, inpaint and outpaint in one workflow—with organized panels, flexible references and previews for every finishing stage.
💬 Discord — help, artwork & updates · ☕ Support on Ko-fi · 🛠️ DonutNodes on GitHub
✨ V5 highlights
Cleaner layout — separate panels for setup, generation, upscaling and face detail.
Inpainting & outpainting — paint or draw a selection, invert it, adjust the seam, or expand with directional canvas presets. Outpainting stays within your megapixel budget.
Smart masks — describe what to select with SAM3.1, or use BiRefNet for foreground/background separation. Refine masks manually.
Independent A/B crops — frame each reference separately, with clipboard paste and optional reference guidance.
Flexible finishing — first and second upscales, Face Detailer and SeedVR2, with individual result previews.
Prompt variants — add, duplicate and reorder prompts; keep one active or cycle automatically. Includes autosizing editors and shared wildcard controls.
Searchable LoRAs — find models by typing, then adjust strengths and block weights.
🚀 Quick start
Install/update DonutNodes 3.0.23+. Restart ComfyUI and refresh your browser.
Open DonutWF_v5.json.
Use Manager → Install Missing Nodes, then restart.
Install the models using one of the options below.
Review your models, LoRAs, prompt and resolution. Leave Editing off for your first text-to-image run, then hit Run.
📦 GitHub installation: use Download missing for the supported model catalog.
📦 Registry/Manager installation: download the optional DonutNodes-model-installer.zip from this version’s files. Extract it, follow the included README and run the Windows or Linux/macOS launcher. It downloads catalog models into the appropriate ComfyUI folders and reuses matching existing files. Some downloads may require an access token.
The Registry package provides model links and the separate installer link instead of the built-in downloader.
🎨 Editing, masks & outpainting
Enable Editing, add your base image to A, and optionally place a second reference in B. Describe the change in the prompt.
Open Paint / outpaint… to edit a selected area or extend the canvas. Use Overlap to let generation reach into the original image and Seam width to soften the transition.
For B, choose Prompt selection to mask a named object, or Auto subject for the foreground. Use full-resolution references for better results.
Reference guidance is a separate option for borrowing visual elements during generation; it pauses while Editing is enabled.
💾 Saving & moving workflows
The supplied preset saves to output/Final with seed-based filenames. Saving supports PNG/WebP workflow metadata.
Keep your old workflow when upgrading, then copy your personal settings into V5. Reference images and wildcard files are stored separately—copy those too when moving installations.
🐛 Feedback
Found a bug? Share your workflow with private content removed, ComfyUI/DonutNodes versions, GPU/VRAM and the full error on Discord.
High-resolution editing with multiple references and NAG can be VRAM-heavy. Seam quality depends on the image, prompt and overlap settings.
Description
updates to custom notes. better face inpainting. removed sdxl because it took forever and required too much vram. probably other stuff.
FAQ
Comments (16)
Brilliant DD, thanks mate !
How do I set a seed value? Instead of generating one every time?
theres a seedgenerator hidden somewhere behind face related only (prompt). its randomized by default.
is possible to add hand refiner / hand detailer?
yeah just do it :)
i cant find the donut face detailer nod. any help? :(
I'll look at it tomorrow..make sure you have updated everything.
@DonutsDelivery thanx for your reply. Everythning is updated but still cant make it work. Nothing is missing in the manager. Is it a custom node i ll have to download or... ?
ive made sure to publish donutnodes once again with most recent changes. idk if that is the cause but try updating now.
@DonutsDelivery any update? commfy manager still missing all donut node and model merge zit node.
@mklwolf Github commits were failing due to a missing secret key. ive now made it so all commits auto publish with comfyui manager using github actions.
finally problem solved!
The DonutFaceDetailer and DonutUniversalDetailer nodes in DonutNodes are optional wrappers/enhancements that depend on ComfyUI-Impact-Pack (by ltdrdata) to function fully (they use its face detection, SEGS, detailer pipes, etc.).
updated the ComfyUI-Impact-Pack and worked just fine :)
hello why are my nsfw prompts not generating at all, only sfw is working for me can someone please help
ZIT is not finetuned on NSFW content yet. And most likely wont be before the base model is released. This is a distilled model that is inferior for training, so they use a de-destilled model, but that isnt optimal either.
@DonutsDelivery hello for some reason i think I managed to get the nsfw to work but its not as strong when giving accurate nsfw outputs however its good enough as the pure raw quality of the image always turns out better, one question i want to ask is how can i use more loras i have downloaded for the generation? im sorry but im fairly new to comfyui, thank you for helping me out
how to use this?