Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
(Also works for any other type of style transfer, but my initial interest was with realism)
Runtime profile
Source description
(Also works for any other type of style transfer, but my initial interest was with realism)
In my time experimenting with realism models I've always been disappointed, as I could never get the sort of creativity, variance, and quality I wanted.
But with Krea 2 I've found something interesting. I'm able to make creative stylized images with a model like Illustrious or Anima, and then run a denoised KSampler over these with Krea 2 to get good realistic-looking results while generally retaining the creative features.
Once you get everything configured right I've found the outputs look even better than what Krea 2 is able to generate through prompting alone.
(It is recommended to use realism LoRAs to help push the effect, as Krea 2 might be insufficient by itself.)
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This workflow turns a stylized image into a realistic-looking image using Krea 2, a denoised KSampler, and a realism-focused prompt, aiming to retain the input’s composition and creative features.
This is the manual-prompting approach; its description says it offers more control than the automatic approach and recommends an LLM to draft a prompt from the input image.
The workflow’s node list includes `LoadImage`, `PreviewImage`, and `SaveImage`.
This version provides a workflow config rather than model files; plan to have the named model files available separately.
Suggestion · not verified
Listed node packs include `comfyui-easy-use`, `comfyui-kjnodes`, and `ComfyUI-Krea2T-Enhancer`.
Also listed are `RES4LYF`, `rgthree-comfy`, and `was-ns`.
Named model files are `krea2Raw_v10.safetensors`, `qwen_image_vae.safetensors`, and `qwen3vl_4b_bf16.safetensors`.
For the realism effect, the author recommends realism LoRAs because Krea 2 alone may be insufficient.
The title includes “Automatic,” while the version label is `v2.0 (manual)` and the description identifies it as manual; verify the selected file if you want the automatic approach.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 2606 downloads · Type Workflows · Base model Krea 2
There are two workflow approaches to this:
An "automatic" workflow which uses the vision of the text encoder to inject information about the input image directly into the prompt, providing a quick and a fairly accurate transfer, but also injecting some stylized information, so it's not ideal.
A "manual" prompting workflow that provides stronger and more controlled realistic style transfer, but requires the use of LLMs to help with the prompting.
Remaining hardware or download-size estimates are not available yet.
Requirements
krea2Raw_v10.safetensors
Not resolvedCheckpoint · Unknown
VAE · 242 MB · SAFETENSORS · Unknown
Text encoder · 8.27 GB · SAFETENSORS · bf16 · Unknown
comfyui-easy-use
FoundNode pack · Registry
Node pack · Registry
Node pack · Registry
RES4LYF
FoundNode pack · Registry
rgthree-comfy
FoundNode pack · Registry
was-ns
Not resolvedNode pack · Registry
