Feature request: instruct-pix2pix #61
Replies: 3 comments 2 replies
-
|
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! |
Beta Was this translation helpful? Give feedback.
-
|
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 failedI may do the PR. Are you sure that this PR will fix my issue if I start it please? |
Beta Was this translation helpful? Give feedback.
-
|
I can try to give it a shot. |
Beta Was this translation helpful? Give feedback.
-
|
Seems easier than I first expected.
We would still need to support separate cfg scales for text and img conditionnings. for better results I think. |
Beta Was this translation helpful? Give feedback.
-
|
@Jonathhhan (I know you asked for it ages ago) and @gogo2464, you can try #679, I think it's working fine now. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Would it be difficult to implement instruct-pix2pix, for example: https://huggingface.co/timbrooks/instruct-pix2pix ?
If I load the
ggmlmodel 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.
Beta Was this translation helpful? Give feedback.
All reactions