A version of the AIT workflow, but this one does img+img, instead of text2img.
[REQUIRED NODES/MODELS]:
-https://github.com/FizzleDorf/AIT
-https://github.com/BlenderNeko/ComfyUI_ADV_CLIP_emb
-THIS IS CRUCIAL: https://huggingface.co/comfyanonymous/clip_vision_g/tree/main
use:
FOR BATCH SIZE 4, YOU MUST HAVE WINDOWS FOR NOW, LINUX WILL BE COMPATIBLE WITH BS4 SOON; IF YOU DON'T WANT BS4, you can change the batch size to 1.
you can weight imageA and imageB according to output; recommended is to start from 1:1, then adjust accordingly if output image is more like imageA than B or the other way around.
speed should be as fast as the normal version of this workflow due to AIT.
Description
FAQ
Comments (1)
Different errors occuring, when trying to launch this thing.
**********************************
Error occurred when executing KSampler:
Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 10.51 GiB
Requested : 25.00 MiB
Device limit : 12.00 GiB
Free (according to CUDA): 0 bytes
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB
******************************************************************
Error occurred when executing KSampler:
cat() received an invalid combination of arguments - got (Tensor, dim=int), but expected one of:
(tuple of Tensors tensors, int dim, , Tensor out)
(tuple of Tensors tensors, name dim, , Tensor out)
******************************************************************
Error occurred when executing KSampler: Error in function: AITemplateModelContainerCreate