Lustify Workflows [Krea 2, SDXL] — SDXL DMD2
This is the workflow that was made with my Lustify models in mind, although other models would obviously work with it too. Please, read all the notes I've left in the workflow!
Runtime profile
- Access
- External workflow
- Status
- Listed
- Version
- lustify8-dmd.json
- Source
- Civitai
- Updated
- Oct 15, 2026
Source description
This is the workflow that was made with my Lustify models in mind, although other models would obviously work with it too. Please, read all the notes I've left in the workflow!
The goal here was to create a setup that utilizes custom nodes only when absolutely necessary. Let's be honest - you don't need 100+ custom nodes to generate great images, and I know exactly what it's like to have obscure nodepacks installed just to use them for a single workflow.
It also utilizes subgraphs, keeping the UI very easy on the eyes and hiding all the noodle spaghetti inside them.
Krea 2 edit related: Get the node from there (I think it's not available via ComfyUI manager right now). Get the identity edit LoRA from there (any of the newer ones). Otherwise the edit functionality wouldn't work.
SDXL related: WARNING! If you use DMD2 workflow, you'll need to do a little bit of manual tweaking, as it utilizes NAG (Normalized Attention Guidance) node for negative prompts to work. And the node hasn't been maintained by it's author for some time already. It's not hard to fix it:
- If you don't have the node installed yet, open your ComfyUI\custom_nodes. Open terminal there and do "git clone https://github.com/ChenDarYen/ComfyUI-NAG.git"
- In the file "custom_nodes\ComfyUI-NAG\chroma\layers.py", change line 5 to: from comfy.ldm.flux.layers import DoubleStreamBlock, SingleStreamBlock
- That's it, the node is now working.
NON-DMD2 Workflow: My personal favorite. It’s slower, and you really need to use most of the custom tools I added to the workflow to get it right. But honestly? It gives the absolute highest quality and most creative results.
DMD2 Workflow: Super fast (6-8 steps) and actually supports negative prompts thanks to NAG. The downside? DMD2 has its own specific visual style, and you do lose a bit of diversity in faces, backgrounds, and textures. Some people prefer this purely for the speed and the vibe.
What you need
- GPU memory
- Sources disagree; inspect the linked recommendations
- Model files
- 15.3 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requirements
Models
9Upscaler · 177 KB · Hugging Face · lij53004/ComfyUI_Models
4x_NMKD-Superscale-SP_178000_G.pth
PossibleUpscaler · Unknown
- Not resolved
Object Detector · Hugging Face
- Not resolved
Object Detector · Hugging Face
- File unverified
VAE · Unknown
lustify_apex_00001_.safetensors
Not resolvedCheckpoint · Unknown
sam_vit_b_01ec64.pth
Not resolvedSegmentation · Unknown
Checkpoint · 15.3 GB · SAFETENSORS · Unknown
xinsir-controlnet-union-sdxl-1.0-promax.safetensors
File unverifiedControlNet · Unknown
Node packs
10comfyui_controlnet_aux
PossibleNode pack · Registry
- Found
Node pack · Registry
Node pack · Registry
Node pack · Registry
- Found
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
- Found
Node pack · Registry
seedvr2_videoupscaler
Not resolvedNode pack · Registry
Sources
1 source
Sources
1 sourceSource excerpts
1 excerpt
Source excerpts
1 excerptSource context: 38990 downloads · Type Workflows · Base model SDXL 1.0
