Recommended Prompts
score_9,score_8_up,score_7_up,source_anime,detailed,veins,toned
score_9,score_8_up,score_7_up,detailed,night
Recommended Negative Prompts
white background
monochrome,toned
| samplers | Euler a, Restart | |
| steps | 14-24 | |
| cfg | 4.0-6.0 | |
| vae | fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors | |
| resolution | 1024×1024 | |
Recommended Hires (High-Resolution) Parameters
| upscaler | 4x-UltraSharp, 4xLexicaDAT2_otf | |
| upscale | 2 | |
| steps | 8 | |
| denoising strength | 0.4-0.5 | |
Tips
Version Highlights
-
Trained as DoRA instead of LoRA
-
Trained with CAME/REX instead of AdamW8Bit
-
cleaned all Watermarks
-
has strong Backgrounds/Scenary
-
3din negative doesnt have much strong effect now -
Details and sharpness increased
-
Can do wonderful dark images now
Settings for generating Images for V2.1:
-
Sampler: Restart
-
Steps: 14-18
-
CFG 4.0-6.0
-
Base Resolution 1024×1024
Creator Sponsors
This is my flagship Incursio’s Meme Diffusion (SDXL, Pony). I find it’s in line with what the community on Civitai likes producing. It’s pretty versatile while also having an artstyle that’s unique in image generation. NSFW compatible.
Refer to the version details for Changelog.
Update:
If you still wanna keep the old Style from V1.6 in V2.1, then you might wanna negate some tags. Here is a small comparison grid.
Also the generator allows both Versions to be used, until I correct out 2.1 a bit.
V2.1:
This Checkpoint is trained on the awesome Basemodel Pony Diffusion V6.
V1.6:
This Checkpoint is trained on the awesome Basemodel AutismMix_confetti.
The only prompt you ever need is this positive prompt:
score_9, score_8_up, score_7_upV1.6 can use source_anime and V2.1 can use detailed as an additional tag. veins is a pretty strong tag, as well as toned in V2.1.
No need for any negatives. Please dont use any or at least only use negatives, that you dont want in your current image. I sometimes use white backgroundin negative only. I’m sick of seeing schizo negatives and schizo positives. I also recommend to not use any () or with weights like (:1.2) on any tags. It can produce some artifacts on your images. To know more about this, check this Article. Anything else for tag related stuff, see Basemodel Pony Diffusion V6.
I also recommend to use the Extension Adetailer, because eyes may not be sharp due to burns.
Settings for generating Images for V1.6:
-
Sampler: Euler a
-
Steps: 24
-
CFG 6.0
-
Base Resolution 1024×1024
Settings for generating Images for V2.1:
-
Sampler: Restart
-
Steps: 14-18
-
CFG 4.0-6.0
-
Base Resolution 1024×1024
Recipe V1.6:
Merge to Checkpoint: TC V Style LoRA PD (LoRA will be released in 1 or 2 weeks) on Weight 0.75 + AutismMix_confetti.
Recipe V2.1:
Merge to Checkpoint: TC V Style LoRA PD V2 on Weight 1.0 + Basemodel Pony Diffusion V6.
Everything else is specified in the image tags. Make sure to leave a review or a comment if you got good use out of this Mix.
How to use Checkpoints’s in auto1111:
-
Download Checkpoint
-
Copy the file to
stable-diffusion-webui/models/Stable-diffusion -
Select your Checkpoint
-
Have Fun!
