Rafie Walker 6761233e9d Implement Self-Attention Guidance (#2201) ... * First SAG test * need to put extra options on the model instead of patcher * no errors and results seem not-broken * Use @ashen-uncensored formula, which works better!!! * Fix a crash when using weird resolutions. Remove an unnecessary UNet call * Improve comments, optimize memory in blur routine * SAG works with sampler_cfg_function		2023-12-13 15:52:11 -05:00
..
chainner_models
nodes_canny.py	Make --gpu-only put intermediate values in GPU memory instead of cpu.	2023-12-08 02:35:45 -05:00
nodes_clip_sdxl.py
nodes_compositing.py	Fix SplitImageWithAlpha and JoinImageWithAlpha.	2023-10-08 15:52:10 -04:00
nodes_custom_sampler.py	Add SDTurboScheduler node.	2023-11-28 13:35:32 -05:00
nodes_freelunch.py	Implement updated FreeU as _for_testing->FreeU_V2 node	2023-10-18 02:06:49 -04:00
nodes_hypernetwork.py	Support hypernetwork with mish activation function and layer norm.	2023-10-17 12:08:03 -04:00
nodes_hypertile.py	Fix hypertile.	2023-12-07 15:22:35 -05:00
nodes_images.py	Fix output APNG not working with ffmpeg.	2023-11-24 18:24:19 -05:00
nodes_latent.py	Add LatentInterpolate to interpolate between latents.	2023-11-20 03:55:51 -05:00
nodes_mask.py	Fix MaskComposite	2023-10-13 13:40:53 -03:00
nodes_model_advanced.py	.sigma and .timestep now return tensors on the same device as the input.	2023-11-27 16:41:33 -05:00
nodes_model_downscale.py	Allow controlling downscale and upscale methods in PatchModelAddDownscale.	2023-11-22 03:23:16 -05:00
nodes_model_merging.py	Add a CLIPSave node to save CLIP model weights.	2023-10-10 01:24:49 -04:00
nodes_post_processing.py	Make --gpu-only put intermediate values in GPU memory instead of cpu.	2023-12-08 02:35:45 -05:00
nodes_rebatch.py	Increase maximum batch size in LatentRebatch.	2023-11-02 13:07:41 -04:00
nodes_sag.py	Implement Self-Attention Guidance (#2201)	2023-12-13 15:52:11 -05:00
nodes_tomesd.py
nodes_upscale_model.py
nodes_video_model.py	Fix typo.	2023-11-23 23:20:07 -05:00