forks/candle.git -

	Commit message (Collapse)	Author	Age	Files	Lines
*	Streamline the glm4 example. (#2694)	Laurent Mazare	2024-12-31	1	-1/+5
\|
*	Add a seed to the flux example. (#2529)	Laurent Mazare	2024-10-02	1	-3/+10
\|
*	Quantized version of flux. (#2500)	Laurent Mazare	2024-09-26	1	-19/+64
\| \| \| \| \| \| \| \| \| \| \| \| \|	* Quantized version of flux. * More generic sampling. * Hook the quantized model. * Use the newly minted gguf file. * Fix for the quantized model. * Default to avoid the faster cuda kernels.
*	Fix FLUX.1 weights (#2457)	Eugene Hauptmann	2024-08-29	1	-3/+3
\| \| \| \| \|	* fix FLUX.1 weights * added flux1-dev.safetensors
*	Support the flux-dev model too. (#2395)	Laurent Mazare	2024-08-04	1	-9/+37
\|
*	Add the flux model for image generation. (#2390)	Laurent Mazare	2024-08-04	1	-0/+182
	* Add the flux autoencoder. * Add the encoder down-blocks. * Upsampling in the decoder. * Sketch the flow matching model. * More flux model. * Add some of the positional embeddings. * Add the rope embeddings. * Add the sampling functions. * Add the flux example. * Fix the T5 bits. * Proper T5 tokenizer. * Clip encoder path fix. * Get the clip embeddings. * No configurable weights in layer norm. * More weights related fixes. * Yet another shape fix. * DType fix. * Fix a couple more shape issues. * DType fixes. * Fix the latent dims. * Fix more shape issues. * Autoencoder fixes. * Get some generations out. * Bugfix. * T5 padding. * Clippy fix. * Add the decode only mode. * Fix. * More fixes. * Finally get some generations to work. * Add readme.