I suspect that you need either Lora or embedding for something this specific. I only found this
1. Attach file
If you don't use a lora, the only chance you have is to generate the picture in txt2txt, go to photoshop and sketch some mask, or even copy paste a mask from some picture, and then in img2img add the ((mask)) to the prompt. If you are lucky, the AI will understand and it will render a perfect mask on your subject.
No way near as bad as I thought it was gonna be.
Sadly the face was lost. I tried different denoising, too high will ruin the video
This video thing needs at least 2 months to be decent, but it's great to get into it to be ready for the video explosion.
They're irrelevant anyway doing those stupid fucking dances. I'd actually like them if they fucking sat still so I could even see their ass properly but instead, they jerk it around like a fucking pinata as if that's fucking arousingWon't anyone think of the tiktok thots!..
| weight 0.8 | weight 0.6 | weight 0.4 |
|
|
|
gif2gif. You can find it in Extensions tab/ Available. Press "load from" .
I think the intricacy is resolution based. Whenever I have a partial shot hips the texture there is out of this world. But the texture disappears the moment I get a full shot of a person. And then I see the texture again in the MrFox's HiRes renders. So, if you want intricate detail down to the pixel, HiRes is where it is at. That's my observation, no idea if shared.
You are probably right, I forgot about resolution, after all this time I still can't understand what is CFG and sampling steps doing to be honest xD
CGF (classifier free guidance) is how much "creative freedom" you give SD and how much you "force" it to adhear to the prompt. If you set it too high the image can get "burnt" but there is a Dynamic Tresholding extension to fix this. There is also an anti burn extension. You can find it in extensions tab/available press "load from". The sample steps is how many attempts SD does to try improve the image. More is not necessarily better. It is better up to a point, then it is changing the composition or add weirdness and artifacs etc. The Hires steps is similar but it has the added function of increasing the quality of details and fidelity etc. Again this is also not something to just crank it to max.
thank you so much, have to try.
For what i've understand it's work like "how much fantasy you need?". let me explain: i work at cfg 11 because is a good value i find work for most prompt i try. but when i do some extreme fantsy promp, especially when you want mix person with animal, i need to lower cfg to 8-7 to get result i want, otherwise i get a person and a animal in image,without mix.
