v1.0.0-beta.33

What's Changed

• Add Aura SR(4x upscale GigaGAN based) support
• Fix #199 gradio version bump
• Guidance scale max value increased to 10

Full Changelog: v1.0.0-beta.32...v1.0.0-beta.33

v1.0.0-beta.32

What's Changed

• Add basic API support by @rupeshs in #194
• Fix typos by @kianmeng in #191

For more details about API checkout readme

New Contributors

• @kianmeng made their first contribution in #191

Full Changelog: v1.0.0-beta.31...v1.0.0-beta.32

Closes #122 #165

v1.0.0-beta.31

What's Changed

• Negative Prompt + Guidance for CLI by @loadfred in #178
• Add experimental support for loading .safetensors SD 1.5 models by @monstruosoft in #163
• Add logging for safetensors loading @rupeshs

New Contributors

• @loadfred made their first contribution in #178

Full Changelog: v1.0.0-beta.30...v1.0.0-beta.31

Tutorial

Checkout this YouTube Tutorial by Nolowiz

v1.0.0-beta.30

What's Changed

• Add Hyper SD 1 step support by @rupeshs in #177
• Add basic benchmarking by @rupeshs in #169
• Fix web UI slider problem #158
• Diffusers, OpenVINO,torch, gradio version bump

For more details on 1 step Hyper-SD inference https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#-fast-1-step-inference-with-hyper-sd

Full Changelog: v1.0.0-beta.29...v1.0.0-beta.30

v1.0.0-beta.29

• Update real-time UI
• Add NPU device check
• Revert the default model to SD-Turbo

Real-time image generation Update 2 :
https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#real-time-text-to-image-experimental

v1.0.0-beta.28

• Add SDXS-512 0.9 support
• Add SDXS-512 0.9 OpenVINO, fast 1-step inference (0.8 seconds to generate 512x512 image)
• Default model changed to SDXS-512-0.9
• Faster real-time image generation
• Enabled OpenVINO Mac on Intel CPUs, Thanks @jamienk

Thanks to new contributor: @jamienk

More details: https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#-fast-1-step-inference-sdxs-512-09

v1.0.0-beta.27

What's Changed

• Add multiple LoRA support by @monstruosoft in #145
• Basic ControlNet v1.1 (LCM-LoRA mode)support by @monstruosoft in #154
• Add ControlNet annotators(Canny,Depth,LineArt,MLSD,NormalBAE,Pose,SoftEdge,Shuffle) @rupeshs
• Update multi-Lora web UI @rupeshs
• Update controller web UI @rupeshs
• Pytroch 2.2 upgrade @rupeshs

How to use Controlnet: https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#controlnet-support

Full Changelog: v1.0.0-beta.26...v1.0.0-beta.27

v1.0.0-beta.26

What's New?

• Add SDXL-Lightning support (LCM mode)
• Add SDXL-Lightning OpenVINO support (int8)

More details : https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#-fast-2-step-inference-sdxl-lightning---adversarial-diffusion-distillation

Full Changelog: v1.0.0-beta.25...v1.0.0-beta.26

v1.0.0-beta.25

What's Changed

• JPEG save support by @rupeshs in #133
• Add lora support for webui, EDSR onnx support by @rupeshs in #144
• Minor changes to tiled upscale code by @monstruosoft in #134
• Update CLI interactive mode by @monstruosoft in #139
• Basic LoRA support by @monstruosoft in #142

How to use Lora models: https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#how-to-use-lora-models

Full Changelog: v1.0.0-beta.24...v1.0.0-beta.25

v1.0.0-beta.24

• Added 2x upscaler (EDSR and Tiled SD upscale (experimental)),thanks monstruosoft for SD upscale
• Works on Android + Termux + PRoot, refer readme
• Closes deprecated parse #106
• Sequential generations support in CLI, thanks [monstruosoft](https://github.com/monst

What's Changed

• Add contributors to readme by @mak448a in #100
• Add CLI img2img by @monstruosoft in #116
• Add CLI image variations by @monstruosoft in #121
• Improved tiled upscale by @monstruosoft in #128
• Abort tiled upscale if using OpenVINO by @monstruosoft in #129

New Contributors

• @mak448a made their first contribution in #100
• @monstruosoft made their first contribution in #116

Full Changelog: v1.0.0-beta.23...v1.0.0-beta.24