gguf quantized version of sd3.5-large (incl. gguf encoder and gguf vae)

• drag sd3.5 to > ./ComfyUI/models/diffusion_models
• drag clip-g, clip-l, t5xxl to > ./ComfyUI/models/text_encoders
• drag vae to > ./ComfyUI/models/vae
• drag demo picture (below) to > your browser for workflow

review

• revised version; load faster than before with full set gguf (model + encoder + decoder)
• upgraded model to fp32; similar file size; shorten loading time; significant difference
• keep both fp16 and fp32 models; you could test it and compare it yourself
• upgraded encoder and decoder to fp32; same file size; better quality

reference

• base model from stabilityai
• comfyui from comfyanonymous
• pig architecture from connector
• gguf-node (pypi|repo|pack)