0.6.5

• Fix FaceID Plus issue with PAG > 0.

Full Changelog: v0.6.4...v0.6.5

0.6.4

• Text encoders, VAE, and image encoder are offloaded to the CPU if partial_cpu_offload is activated.
• Multiple masks per IP Adapter model are now supported.
• New IP Adapter models added.
• Fixed a bug in CLIPTextModel.

Full Changelog: v0.6.3...v0.6.4

0.6.3

• Added support for using a custom detector model with adetailer.
• Strength and Prompt emphasis are now included in the image metadata.
• Added "timestamp" option to filename_pattern for saving images with the current time.
• Added experimental prompt emphasis.

Full Changelog: 0.6.2...v0.6.3

0.6.2

Full Changelog: 0.6.1...0.6.2

0.6.1

Full Changelog: 0.6.0...0.6.1

0.6.0

What's Changed

• dev branch by @R3gm in #19

Full Changelog: 0.5.2...0.6.0

0.5.2

Full Changelog: 0.5.1...0.5.2

0.5.1

• After generation, PIL images are now returned along with sublists containing the seeds, image paths, and metadata with the parameters used in generation. [pil_image], [seed, image_path, metadata]
• The use of image_previews=True has been improved, and now preview images can be obtained during the generation steps using a generator. For more details, refer to the Colab notebook.

0.5.0

Version 0.5.0: New Update Details

• Fix LoRA SDXL compatibility.
• Latent upscaler and variants.
• Perturbed Attention Guidance (PAG) enhances image generation quality without the need for training.
• Multiple images for one FaceID adapter.
• ControlNet for SDXL: MLSD, Segmentation, Normalbae.
• ControlNet "lineart_anime" task accessible and able to load a model different from the "lineart" task.
• ControlNet Tile and Recolor for SD1.5 and SDXL ("tile" replaces the previous task called "sdxl_tile_realistic").

0.4.1

• Fix the aspect ratio for SDXL inpaint