TXT2IMG Simplified SDXL with Refiner & LoRA stack + UltSDUpscale
created 10 months ago
upscale
4 nodes

1.9k

548

Outputs
example image output 0 for workflow.
example image output 1 for workflow.
example image output 2 for workflow.
example image output 3 for workflow.
example image output 4 for workflow.
example image output 5 for workflow.
example image output 6 for workflow.
example image output 7 for workflow.
example image output 8 for workflow.
example image output optimized_comfy_workflows_user_uploads/694ec465-7d96-4361-b78a-2b2025837d08/assets/ComfyUI_temp_elmss_00005_.webp for workflow.
Description

Globby J's Simplified SDXL Text to Image + Upscale Workflow.

The workflow consists of 3 major Group Nodes.

Top Left: SDGEN1

This group node consists of the Checkpoint Loader, VAE loader (for if you're not using a checkpoint with baked in VAE), Positive and Negative Prompt Text Boxes, and 4 LoRA Stack (Reduce strength values to 0 to disable that LoRA)

Bottom Left: SD+REF

This group node contains the KSampler for both the initial SDXL generation, and the KSampler for the refiner. Options for both these samplers are included. (refiner options last).

Once the refiner is finished, an image of the generation will be displayed at the bottom of this group node.

Right: UPSCALE

This group node contains all necessary nodes for the UltimateSDUpscale. After the upscale is completed, the upscaled image will be displayed at the bottom of this group node. This image is not automatically saved (in order to preserve storage space), You can right click and manually save the image or open it in a browser window.

Find these notes within the workflow as well. ENJOY!

Built-in nodes
Custom nodes
UpscaleModelLoader
UltimateSDUpscale
PreviewImage
CheckpointLoaderSimple
VAELoader
PrimitiveNode
LoraLoader
CLIPTextEncode
KSampler
VAEDecode
Models
3
0
1
0