add support for load textual inversion embeddings

[zhaojinzhou]

hope to support embeddings format end with .pt

[daniandtheweb]

It already supports embeddings. You can call them with:

./sd ....  --embd-dir embedding_dir -p "prompt, embedding:embeddingname"

[zhaojinzhou]

It already supports embeddings. You can call them with:

./sd ....  --embd-dir embedding_dir -p "prompt, embedding:embeddingname"

but when I use badhand_v4.pt, It throws exception, and log error info : using checkpoint format It dost not work.

[zhaojinzhou]

It already supports embeddings. You can call them with:

./sd ....  --embd-dir embedding_dir -p "prompt, embedding:embeddingname"

[daniandtheweb]

Can you send your full launch code and / or log?

[zhaojinzhou]

Can you send your full launch code and / or log?

[INFO ] stable-diffusion.cpp:501 - loading model from 'bWFqaWN2Ni5zYWZldGVuc29ycwo=' completed, taking 0.42s [INFO ] stable-diffusion.cpp:528 - running in eps-prediction mode [INFO ] stable-diffusion.cpp:655 - Attempting to apply 0 LoRAs [INFO ] stable-diffusion.cpp:1132 - apply_loras completed, taking 0.00s [INFO ] model.cpp:796 - load embeddings/FastNegativeV2.pt using checkpoint format /root/stable-diffusion.cpp/ggml/src/ggml-cuda/concat.cu:157: GGML_ASSERT(src0->type == GGML_TYPE_F32) failed Aborted (core dumped) root@bc413b608e61:~# ls embeddings/ FastNegativeV2.pt bad-picture-chill-75v.pt badhandv4.pt ng_deepnegative_v1_75t.pt root@bc413b608e61:~# ./trainer_cpp -m bWFqaWN2Ni5zYWZldGVuc29ycwo= -p 'sexy girl 20_years_old' -n 'bad hands, FastNegativeV2' --steps 20 --embd-dir embeddings

[zhaojinzhou]

Can you send your full launch code and / or log?

[INFO ] stable-diffusion.cpp:501 - loading model from 'bWFqaWN2Ni5zYWZldGVuc29ycwo=' completed, taking 0.42s [INFO ] stable-diffusion.cpp:528 - running in eps-prediction mode [INFO ] stable-diffusion.cpp:655 - Attempting to apply 0 LoRAs [INFO ] stable-diffusion.cpp:1132 - apply_loras completed, taking 0.00s [INFO ] model.cpp:796 - load embeddings/FastNegativeV2.pt using checkpoint format /root/stable-diffusion.cpp/ggml/src/ggml-cuda/concat.cu:157: GGML_ASSERT(src0->type == GGML_TYPE_F32) failed Aborted (core dumped) root@bc413b608e61:~# ls embeddings/ FastNegativeV2.pt bad-picture-chill-75v.pt badhandv4.pt ng_deepnegative_v1_75t.pt root@bc413b608e61:~# ./trainer_cpp -m bWFqaWN2Ni5zYWZldGVuc29ycwo= -p 'sexy girl 20_years_old' -n 'bad hands, FastNegativeV2' --steps 20 --embd-dir embeddings

cublas version

[daniandtheweb]

I've been using the vulkan version before and there it worked but I'm now on the cublas version and you're right, there this fails. Apparently the needed operations to handle the embeddings still haven't been added.

However the issue isn't about the .pt format, I think it's about embeddings in general as also easynegative.safetensors doesn't work. I haven't been able to use any embedding for now on cublas.