Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-05-01 | checkpoint override enhancement | w-e-w | |
2023-04-29 | Merge branch 'dev' into master | AUTOMATIC1111 | |
2023-04-29 | add is_hr_pass field for processing | AUTOMATIC | |
2023-04-29 | rework Negative Guidance minimum sigma to work with AND, add infotext and ↵ | AUTOMATIC | |
copypaste parameters support | |||
2023-04-29 | Merge pull request #9177 from devNegative-asm/master | AUTOMATIC1111 | |
(Optimization) Option to remove negative conditioning at low sigma values | |||
2023-04-29 | Merge pull request #9628 from catboxanon/patch/9092 | AUTOMATIC1111 | |
Fix image mask/composite for weird resolutions | |||
2023-04-29 | Merge pull request #9669 from catboxanon/patch/sampler-schedule-fix | AUTOMATIC1111 | |
Fix prompt schedule for second order samplers | |||
2023-04-29 | rename CPU RNG to RNG source in settings, add infotext and parameters ↵ | AUTOMATIC | |
copypaste support to RNG source | |||
2023-04-16 | Update processing.py | catboxanon | |
2023-04-16 | Modify step multiplier flow | catboxanon | |
2023-04-16 | Fix sampler schedules with step multiplier | catboxanon | |
2023-04-14 | Only handle image mask if any option enabled | catboxanon | |
2023-04-14 | Fix image mask composite for weird resolutions | catboxanon | |
2023-04-07 | Add [batch_number] and [generation_number] filename patterns | gk | |
2023-04-06 | Add support for saving init images in img2img | For Sure | |
2023-03-28 | performance increase | devdn | |
2023-03-28 | Revert "Merge pull request #7931 from space-nuko/img2img-enhance" | AUTOMATIC | |
This reverts commit 426875937048e21305ac24bea53df06523bdaa81, reversing changes made to 1b63afbedc7789c0eb9a4742b780ab304d7a9caf. | |||
2023-03-28 | Merge pull request #7931 from space-nuko/img2img-enhance | AUTOMATIC1111 | |
Add `Upscale by` and `Upscaler` options to img2img | |||
2023-03-28 | Merge pull request #8958 from MrCheeze/variations-model | AUTOMATIC1111 | |
Add support for the unclip (Variations) models, unclip-h and unclip-l | |||
2023-03-25 | Add support for the Variations models (unclip-h and unclip-l) | MrCheeze | |
2023-03-25 | Add upscaler to img2img | space-nuko | |
2023-03-25 | Add upscale slider to img2img | space-nuko | |
2023-03-22 | Expose inpainting mask and composite | catboxanon | |
For inpainting, this exposes the mask and masked composite and gives the user the ability to display these in the web UI, save to disk, or both. | |||
2023-03-13 | initialize extra_network_data before use | high_byte | |
2023-03-11 | Merge pull request #8017 from space-nuko/before-process-batch | AUTOMATIC1111 | |
Add `before_process_batch` script callback | |||
2023-03-10 | Merge remote-tracking branch 'origin/master' into unipc | space-nuko | |
2023-02-22 | Add before_process_batch script callback | space-nuko | |
2023-02-19 | fix the a merge conflict resolve i did that entirely breaks image generation | AUTOMATIC | |
2023-02-19 | Merge branch 'master' into fix-save-params-2 | AUTOMATIC1111 | |
2023-02-16 | Fix params.txt saving for infotexts modified by process_batch | space-nuko | |
2023-02-13 | Apply extra networks per-batch instead of per-session (fixes wildcards) | space-nuko | |
2023-02-10 | bug fix | space-nuko | |
2023-02-10 | UniPC does not support img2img (for now) | space-nuko | |
2023-02-10 | Working UniPC (for batch size 1) | space-nuko | |
2023-02-03 | txt2img Hires Fix | Kyle | |
2023-02-03 | Image CFG Added (Full Implementation) | Kyle | |
Uses separate denoiser for edit (instruct-pix2pix) models No impact to txt2img or regular img2img "Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model | |||
2023-02-02 | Processing only, no CFGDenoiser change | Kyle | |
Allows instruct-pix2pix | |||
2023-02-02 | Revert "instruct-pix2pix support" | Kyle | |
This reverts commit 269833067de1e7d0b6a6bd65724743d6b88a133f. | |||
2023-02-02 | instruct-pix2pix support | Kyle | |
2023-01-30 | make the program read Eta and Eta DDIM from generation parameters | AUTOMATIC | |
2023-01-29 | remove Batch size and Batch pos from textinfo (goodbye) | AUTOMATIC | |
2023-01-28 | Merge pull request #7309 from brkirch/fix-embeddings | AUTOMATIC1111 | |
Fix embeddings, upscalers, and refactor `--upcast-sampling` | |||
2023-01-28 | Refactor conditional casting, fix upscalers | brkirch | |
2023-01-27 | add data-dir flag and set all user data directories based on it | Max Audron | |
2023-01-26 | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | |
fix some style inconsistenices | |||
2023-01-26 | Fix full previews, --no-half-vae | brkirch | |
2023-01-25 | add edit_image_conditioning from my earlier edits in case there's an attempt ↵ | AUTOMATIC | |
to inegrate pix2pix properly this allows to use pix2pix model in img2img though it won't work well this way | |||
2023-01-25 | Merge pull request #6510 from brkirch/unet16-upcast-precision | AUTOMATIC1111 | |
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half | |||
2023-01-25 | change to code for live preview fix on OSX to be bit more obvious | AUTOMATIC | |
2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | |
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers. In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also. |