Forum Replies Created
-
Posts
-
This could be a memory issue. You can try restarting your PC to see if that helps. SD Forge should have all optimization set out of the box.
A checkpoint model is a Stable Diffusion model which generates images from text.
Instant ID is an add-on model to a checkpoint model to copy faces. You cannot use instant id on its own. It has to be used with a checkpoint model. (Same for photo maker)
Re: not getting good result with instant ID: Try using it with a realistic model (e.g. Juggernaut XL) and a realistic prompt. Use a high res picture.
Hi, I don’t quite get what you are asking. By IP, do you mean Image Prompt adapter? Are you referring to a comfyui workflow or a general technical question?
This is quite an uncharted area because it is a rare use case. You can start with 7-10 images and see if dreambooth works. Otherwise, you will need to experiment with more images or other techniques.
Hi! Very interesting application. This one is tough because I don’t think SD would have seen this in its training.
If you have a good number of sample images, you can try training a LoRA or Dreambooth model with specific prompts.
Forgot to mention that there’s a new tutorial on this
You can try the following to see which one works better
- Add training images with your face in a similar size (pixels)
- Use inpainting (masked only) at 0.5 or so to redraw the face at a higher resolution.
when you use high CFG values like 20, you usually get a color-saturated image. Dynamic CFG thresholding is a technique to constraint the sampling process to reduce the saturation effect.
Hi, it seems that your trained model is not stable. You can:
- Train from SD 1.5 if possible. The model is in a better state compared to realistic vision.
- Try reducing the number of training steps and/or learning rate. Use the least you can get away with.