New Release - Happy Holidays #2654
vladmandic
announced in
Announcements
Replies: 3 comments 2 replies
-
Happy Holidays to you too!!! Thank you a lot for all the work you and the team did, words are not enough to express my gratitude. Since this is a massive update do you recommend doing a fresh install or a normal update is enough? |
Beta Was this translation helpful? Give feedback.
1 reply
-
Awesome, thanks for your time and effort :) |
Beta Was this translation helpful? Give feedback.
0 replies
-
how to make a theme like the one on the second screen? |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Happy holidays everyone!
To wrap up this amazing year, we're releasing a new version of SD.Next, this one is absolutely massive!
For full list of changes, see Changelog (it really is too long to post here)
Highlights
Native implementation of all control methods for both SD15 and SD-XL
▹ ControlNet | ControlNet XS | Control LLLite | T2I Adapters | IP Adapters
For details, see Wiki documentation:
This brings number of supported t2i/i2i model families to 13!
▹ Stable Diffusion 1.5/2.1 | SD-XL | LCM | Segmind | Kandinsky | Pixart-α | Würstchen | aMUSEd | DeepFloyd IF | UniDiffusion | SD-Distilled | BLiP Diffusion | etc.
▹ AnimateDiff | SVD | ModelScope | ZeroScope
▹ Windows | Linux | MacOS with nVidia | AMD | IntelArc | DirectML | OpenVINO | ONNX+Olive backends
with all model types available for single click download & load (networks -> reference)
For comparisment of different processing options and compile backends, see Wiki
As a highlight, we're reaching ~100 it/s (no tricks, this is with full features enabled and end-to-end on a standard nVidia RTX4090)
And others improvements in areas such as: Upscaling (up to 8x now with 40+ available upscalers), Inpainting (better quality), Prompt scheduling, new Sampler options, new LoRA types, additional UI themes, better HDR processing, built-in Video interpolation, parallel Batch processing, etc.
Plus some nifty new modules such as FaceID automatic face guidance using embeds during generation and Depth 3D image to 3D scene
Links: Home | Readme | Changelog | Wiki | Discord
Beta Was this translation helpful? Give feedback.
All reactions