(illustrious was the base, if I'm not mistaken). A merge of my PonyXL model, (Adamah Mix XL - v1.5 | Stable Diffusion Checkpoint | Civitai ), PaSancturary ( PaSanctuary (SDXL, IllustriousXL) - v1.0 | Stable Diffusion XL Checkpoint | Civitai ), IllustriousXL ( Illustrious-XL - v0.1 | Stable Diffusion XL Checkpoint | Civitai ) and a bit of Luceron ( Lucereon | Artists Finetune | IllustriousXL - v1.0 | Stable Diffusion XL Checkpoint | Civitai ) It can do most of the pony loras I have messed with (i'm not sure why some didn't work), every IllustriousXL Lora i've used, and I tested two SDXL and they didn't work. used a combination of Weight sum and DARE merges at low weights. (PONY DORAS DON'T WORK, HAVEN'T TESTED ILLUSTRIOUS ONES). I don't think SDXL Loras work. Artist tags and character tags work, I recommend putting artists near the beginning any lowering the weight since some of them are strong. Can use Pony and Illustrious Loras at the same time (at least from my testing it seemed to work)
V1.2 - Mixed in MFCG Grill Mix ( MFCG Grill Mix - v1.0 | Stable Diffusion XL Checkpoint | Civitai )
V1.4 - mixed Noobai Epsilo-pred-0.5 ( NoobAI-XL (NAI-XL) - Epsilon-pred 0.5-Version | Stable Diffusion XL Checkpoint | Civitai )
V1.4 - mixed Pasancturary V2
V1.5 Mixed SpatterXL V1 - Pasancturary has tags for anime and realistic, so you can add those to get different styles
V1.6 - MorgyMixV2 ( MorgyMix-illustriousXL - v2.0 | Illustrious Checkpoint | Civitai )
V1.7 Anzhc's model ( AAA(AAAAAAAAAAAAAAAAAAAA) | Finetune mix on whatever model i want at that point which is Illustrious XL right now,but i will keep Pony one for on-site as well - Update. | Illustrious Checkpoint | Civitai )
Recommended positive: (Score_9, score_7:0.6), masterpiece, best quality, good quality, newest, (I don't think pony scores should be used, they can drastically change the image and makes it not follow artstyles as well)
Recommended Negative: lowres, worst quality, bad quality, bad anatomy, jpeg artifacts, signature, watermark24 - 32 steps, Eular A, Align Your Steps (DPM++ 3M SDE seems to work good for thick, rough, or messy illustrations/ sketches) (DPM++ 3M SDE and SGM Uniform work good from my testing)
CFG 4 - 7
These are just what I use, check the other models for more tips
(will try to see if I can merge to get SDXL loras working at some point)
SpatterXL (IllustriousXL X PonyXL) is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user bloodsplash. Derived from the powerful Stable Diffusion (Illustrious) model, SpatterXL (IllustriousXL X PonyXL) has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that SpatterXL (IllustriousXL X PonyXL) is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, concept, illustration.
With a rating of 0 and over 0 ratings, SpatterXL (IllustriousXL X PonyXL) is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of SpatterXL (IllustriousXL X PonyXL) from here.
To use SpatterXL (IllustriousXL X PonyXL), download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like SpatterXL (IllustriousXL X PonyXL), check out our crash course in AI image generation.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.