Simple Vector Flux
Simple Vector Flux was trained on a curated dataset of ~50 synthetic images in classic vector style, 15 epochs, 2 repeats, ~1500 steps.
This is a work in progress and it can be a little temperamental, the captioning was done using Joy Caption Batch with the trigger "v3ct0r" and "vector" in the prefix of the captions.
You have to work a little bit to get desired results and sometimes there is bleeding/blending of subjects but overall the style is present and the results can be really good. This LoRA takes a couple of tries adjusting your prompt and adding tokens to match the style. Expect a second version of this LoRA soon.
If you enjoy this resource please send BUZZ ⚡️so I can keep experimenting and sharing. Please share your images in the gallery after downloading them, by sharing them in the gallery the system gives creators buzz to help with generating and training.
Trigger keyword: 'v3ct0r'
Recommended strengths: 0.6 - 0.9
Description
FAQ
Comments (7)
Any way to output or convert these into SVG's? Would be create for 2D animation software.
VTracer and Vectorizer.ai are the only two I’ve tried, I prefer Vectorizer but it’s paid. There are also svg conversion nodes you install in ComfyUI.
GIMP has a trace bitmap tool
There is Auto1111 extension called stable-diffusion-webui-vectorstudio, but currently you can't run Flux there yet.
@renderartist how this custom node is called?
Nice lora to make simple image for my classes
Lora works well with other Loras without distorting, which is relevant when drawing portraits.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.