Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

PastelartXL - Pastel drawings style LoRA

please consider sharing some of your images with this LoRA - I'd love to see them!

As with all my LoRAs, my focus is on getting a true, dependable, and authentic style that's as versatile as possible. Prompt for anything and have it rendered in a beautiful pastel style!

If you've ever drawn with pastels, you know they're not the most precise medium in the world. This LoRA stays generally true to that and gives a lot of generalized backgrounds and forms. Markmaking is pronounced and colors often very discrete with minimal blending. Some output may tend toward cartoon but that, again, is fairly true to the medium. You can mitigate it a bit by using 'cartoon' and 'anime' in the negative prompt if you need.

Recommended settings for use:

You can go here (pastebin) to download a ComfyUI workflow similar to my usual workflow, but without custom nodes.

  • Start with a full 1.0 LoRA strength and adjust down if you need.

  • I have so far just tested with base SDXL1.0 and can't comment on how well it will work with various fine tunes.

  • I recommend the DPM samplers, but use your favorite. Some may produce softer styles that don't suit my taste as much but whatever you prefer is great.

  • Keywords can have strong effects. I start with 'drawing in pastels of ...'
    If instead you prompt 'pastel drawing of ...' you are more likely to influence coloring toward pastels (mixed with white) whereas the former leans toward more naturalistic coloring.
    if you simply prompt 'drawing of ...' you can get a rather more different style still that changes depending on the subject matter

  • Feel free to add artist names (Klimt, Mucha, etc) and the LoRA will merge its style with theirs with dependable, and usually very pleasing, results.

I'm happy to share my work for free, just as the base model SDXL came free to us all. But if you felt compelled to offer some material form of thanks, you can buy me a coffee, or you can buy my (darn near unreadable, I warn you) short story 'Willem & Ellene'.

Images Generated With This Model

Loading...

Similar Models

Neon Cyberpunk Splash Art FLUX, SDXL, Pony & SD1.5
V1
Neon Cyberpunk Splash Art FLUX, SDXL, Pony & SD1.5
(0.00)
0
0 Ratings
Xray XL LoRA
V2
Xray XL LoRA
(5.00)
0
1 Ratings
Classic infinite
V1
Classic infinite
(0.00)
0
0 Ratings
Porcellana(SD 1.5)
V1
Porcellana(SD 1.5)
(5.00)
0
2 Ratings
ParchartXL
V2
ParchartXL
(0.00)
0
0 Ratings
ReSousou 热馊馊 style
V1
ReSousou 热馊馊 style
(0.00)
0
0 Ratings
Ivan Belikov SDXL 1.0 art style lora
V2
Ivan Belikov SDXL 1.0 art style lora
(5.00)
0
1 Ratings
ClassipeintXL (oil paint / oil painting style)
V2
ClassipeintXL (oil paint / oil painting style)
(0.00)
0
0 Ratings
[OUTDATED] Zeitgeist - Dark and Darker (Style LoRa for SDXL)
V2
[OUTDATED] Zeitgeist - Dark and Darker (Style LoRa for SDXL)
(0.00)
0
0 Ratings
Queratogray Sketch (eddiemauro-mix) LORA
V1
Queratogray Sketch (eddiemauro-mix) LORA
(2.00)
0
1 Ratings

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.