fix: optimize the handling of CLIP embedding weight (leejet#840)

fix: serialize calls to ggml_backend_tensor_set

feat: add detailed tensor loading time stat (leejet#793)

sync: update ggml, make cuda im2col a little faster

feat: add missing models and parameters to image metadata (leejet#743)

* feat: add new scheduler types, clip skip and vae to image embedded params

- If a non default scheduler is set, include it in the 'Sampler' tag in the data
embedded into the final image.
- If a custom VAE path is set, include the vae name (without path and extension)
in embedded image params under a `VAE:` tag.
- If a custom Clip skip is set, include that Clip skip value in embedded image
params under a `Clip skip:` tag.

* feat: add separate diffusion and text models to metadata

---------

Co-authored-by: one-lithe-rune <[email protected]>

sync: update ggml

fix: make --taesd work (leejet#731)

feat: add Instruct-Pix2pix/CosXL-Edit support (leejet#679)

* Instruct-p2p support

* support 2 conditionings cfg

* Do not re-encode the exact same image twice

* fixes for 2-cfg

* Fix pix2pix latent inputs + improve inpainting a bit + fix naming

* prepare for other pix2pix-like models

* Support sdxl ip2p

* fix reference image embeddings

* Support 2-cond cfg properly in cli

* fix typo in help

* Support masks for ip2p models

* unify code style

* delete unused code

* use edit mode

* add img_cond

* format code

---------

Co-authored-by: leejet <[email protected]>

feat: add support for f64/i64 and clip_g diffusers model (leejet#681)

feat: make lora graph size variable