Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This workflow is an update - and a massive upgrade - from the older merge workflows.
Runtime profile
Source description
This workflow is an update - and a massive upgrade - from the older merge workflows.
The intent of this workflow is to simplify surreal compositions by generating two separate images which are then combined into a single merged image.
The strength of each image as well as the composition of the image can be controlled through the latent blend , model sampling, and LoRA model_strength knobs.
Finally, that image is then passed off to the re-renderer/refiner for the final 4-10 steps.
The LoRA can be found here: https://civitai.com/models/2264765?modelVersionId=2549232
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
XUPLX_Unusual_Workflow is for creating surreal image compositions: its main path takes two generated images and produces one merged image for re-rendering or refinement, while its standalone path takes one prompt and produces a simple image.
The main path generates two separate images, combines them into one merged image, and sends the result to a re-renderer or refiner.
The standalone portion connects the LoRA loader and standard nodes for simple images from a single prompt.
The composition path uses two generated images and produces a merged image; the standalone path uses one prompt and produces a simple image.
It is a Workflows item from ExportAnything and uses ZImageTurbo as its base model.
The listed model files are ae.safetensors, qwen_3_4b.safetensors, XUPLX_UnusualPhotoMontageLoRA.safetensors, and z_image_turbo_bf16.safetensors.
The listed node packs are ComfyUI_Comfyroll_CustomNodes, comfyui_fizznodes, comfyui-easy-use, and comfyui-mixlab-nodes.
Additional listed node packs are comfyui-rvtools_v2 and pr-was-node-suite-comfyui-47064894.
Adjust latent blend, model sampling, and LoRA model_strength to control each image’s strength and the composition.
The LoRA is intended for late-stage use during generation to push the result toward a surreal image composition.
Before use, verify that all listed model files and node packs are available in your environment.
Suggestion · not verified
License information is not listed, so check the applicable terms before using it.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 144 downloads · Type Workflows · Base model ZImageTurbo
What does this workflow do?
The intent of the workflow is for the LoRA to be used late-stage during the generation process to force the output into a surreal image composition.
What is included in this workflow?
The top portion of the workflow (as seen in the images) is where the images are merged to create far-out compositions.
The workflow also comes with a stand-alone portion where just the LoRA loader and the standard nodes are connected to create simple images with just a single prompt.
DON'T BUY ME A COFFEE!!
Download ExportGPT - Media & Chat Export Toolkit from the Chrome Web Store. The chrome extension works with ChatGPT and Sora to export assets quickly. I update it often, it has 5 stars, and it's free forever!
Visit exportgpt.org to see it in action.
Estimated VRAM requirement
Estimate unavailable
Model file sizes are not complete enough to calculate this requirement yet.
Requirements
10 requirementsVAE · Unknown
XUPLX_UnusualPhotoMontageLoRA.safetensors
Not resolvedLoRA · Unknown
z_image_turbo_bf16.safetensors
File unverifiedCheckpoint · Unknown
Node pack · Registry
Node pack · Registry
Node pack · Registry
comfyui-mixlab-nodes
PossibleNode pack · Registry
Node pack · Registry
pr-was-node-suite-comfyui-47064894
Not resolvedNode pack · Registry
