Feature request: instruct-pix2pix

[Jonathhhan]

Would it be difficult to implement instruct-pix2pix, for example: https://huggingface.co/timbrooks/instruct-pix2pix ?
If I load the ggml model I get the error:
stable-diffusion.cpp:3045 - tensor 'model.diffusion_model.input_blocks.0.0.weight' has wrong shape in model file: got [3, 3, 8, 320], expected [3, 3, 4, 320]
I can run the inference, but the result is a black image.

[gogo2464]

I have exactly the same issue! @Jonathhhan Could you tell me if I can convert this file to gguf to fix the issue quick please?

I would love to do it sadly I fear I do not have the time for a PR. Sorry!

[gogo2464]

I have exactly the error:

./sd -m dir/liberty_main.instruct-pix2pix.safetensors -H 64 -W 64 --prompt "pikachu"
[INFO ] stable-diffusion.cpp:197  - loading model from 'dir/liberty_main.instruct-pix2pix.safetensors'
[INFO ] model.cpp:908  - load dir/liberty_main.instruct-pix2pix.safetensors using safetensors format
[INFO ] stable-diffusion.cpp:244  - Version: SD 1.x 
[INFO ] stable-diffusion.cpp:277  - Weight type:                 f32
[INFO ] stable-diffusion.cpp:278  - Conditioner weight type:     f32
[INFO ] stable-diffusion.cpp:279  - Diffusion model weight type: f32
[INFO ] stable-diffusion.cpp:280  - VAE weight type:             f32
  |===================>                              | 446/1131 - 0.00it/s[ERROR] model.cpp:1906 - tensor 'model.diffusion_model.input_blocks.0.0.weight' has wrong shape in model file: got [3, 3, 8, 320], expected [3, 3, 4, 320]
[WARN ] model.cpp:1791 - process tensor failed: 'model.diffusion_model.input_blocks.0.0.weight'
[ERROR] model.cpp:1922 - load tensors from file failed
[ERROR] stable-diffusion.cpp:441  - load tensors from model loader failed
new_sd_ctx_t failed

I may do the PR. Are you sure that this PR will fix my issue if I start it please?