!!! Experimental supported by gpustack/llama box v0.0.84+ only !!! Model creator : Freepik Original model : flux.1 lite 8B alpha GGUF quantization : based on stable diffusion.cpp ac54e that patched by llama box. Quantization OpenAI CLIP ViT L/14 Quantization Google T5 xxl Quantization VAE Quantization FP16 FP16 FP16 FP16 Q8 0 FP16 Q8 0 FP16 (pure) Q8 0 Q8 0 Q8 0 FP16 Q4 1 FP16 Q8 0 FP16 Q4 0 FP16 Q8 0 FP16 (pure) Q4 0 Q4 0 Q4 0 FP16 Flux.1 Lite We are thrilled to announce the alpha release of Flux.1 Lite, an 8B parameter transformer model distilled from the FLUX.1 dev model. This version uses 7 GB less RAM and runs 23% faster while maintaining the same precision (bfloat16) as the original model. Text to Image Flux.1 Lite is ready to unleash your creativity! For the best results, we strongly recommend using a guidance scale of 3.5 and setting n steps between 22 and 30 . Motivation Inspired by Ostris findings, we analyzed the mean squared error (MSE) between the input and output of each block to quantify their contribution to the final result, revealing significant variability. As Ostris pointed out, not all blocks contribute equally. While skipping just one of the early MMDiT or lat…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy