I try to pin images that stand out / i personally like every 1-3 weeks
So if i unpin yours doesnt mean that i dont like it anymore just trying to keep a fresh rotation of images without completly filling the start page with pins <3
Join the Discord for questions / sharing pictures :) : https://discord.gg/gcJqAKQ5Af
If you enjoy my models and want to support me, you can now support me on kofi
(Since my patreon got disabled like a year ago & buy me a coffee banned me 4.2026 )
🛠️ Recommended Settings:
Resolution:
best results with832x1216//960x1440//1024x1024//1024x1536CFG Scale:
5–8Sampling Method:
Euler aorDPM++ 2M KarrasSteps:
20–50
Description
FAQ
Comments (10)
i missed this perfect checkpoint👌💯 .. can't wait for the version 5-FP16 ❤️
true
@devilkad having some internet problems but pruned version is uploading :)
thank you very much 🥰.. btw it's all over the world those internet outages and issues @DesyncÂ
@devilkad yep its uploaded btw :)
The best I've tried! Tell me, can I somehow register complete darkness? For example, do I want headlights in complete darkness? The model ignores me not to write in favor of darkness... (
I can suggest three ways to try to get a specific effect. You will need one or more images showing the effect you want. The quickest and easiest (but least powerful) thing you can try is Image to Prompt: https://stable-diffusion-art.com/prompts-from-images/ With luck you'll find one or more keywords or phrases in the suggested prompts that will trigger the effect you want. The much more powerful options are to train a Textural Inversion or a LORA using several example images. Textural Inversion or a LORA gives you a new keyword you can put in your prompts to get the effect you want. Training one of them takes some time, it's more technical and you'll need to be able to learn/follow more technical instructions, it needs decent hardware, and the results will be as good or bad as your sample images and training quality. You'll have to google Textural Inversion or a LORA for more info.
There's a lora called LowRa that's pretty good at making low gamma or nighttime images. https://civitai.com/models/221845/lowra-offset-noise
Is it mix of Deliberate? Same broken anatomy - streched bodies even on demo images which expected to be if not perfect, but at least not wrong.
A fairly high-quality semi-realistic merge. The results are very similar to Lyriel. In general, there is nothing to complain about, a good model.
Thank you.
Details
Files
perfectdeliberate_v5SD15.safetensors
Mirrors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5SD15.safetensors
perfectdeliberate_v5SD15.safetensors
perfectdeliberate_v5SD15.safetensors
pd.safetensors
Desync Image v5.safetensors
perfectdeliberate_v5.safetensors
perfectdeliberate_v5_1.safetensors
perfectdeliberate_v5.safetensors



















