801 Commits (master)

Author SHA1 Message Date
comfyanonymous 8cc75c64ff Let unet wrapper functions have .to attributes. 1 year ago
comfyanonymous 5e885bd9c8 Cleanup. 1 year ago
Yukimasa Funaoka 9eb621c95a
Supports TAESD models in safetensors format 1 year ago
comfyanonymous 72188dffc3 load_checkpoint_guess_config can now optionally output the model. 1 year ago
Jairo Correa 63e5fd1790 Option to input directory 1 year ago
City 9bfec2bdbf Fix quality loss due to low precision 1 year ago
badayvedat 0f17993d05 fix: typo in extra sampler 1 year ago
comfyanonymous 66756de100 Add SamplerDPMPP_2M_SDE node. 1 year ago
comfyanonymous 71713888c4 Print missing VAE keys. 1 year ago
comfyanonymous d234ca558a Add missing samplers to KSamplerSelect. 1 year ago
comfyanonymous 1adcc4c3a2 Add a SamplerCustom Node. 1 year ago
comfyanonymous bf3fc2f1b7 Refactor sampling related code. 1 year ago
comfyanonymous fff491b032 Model patches can now know which batch is positive and negative. 1 year ago
comfyanonymous 1d6dd83184 Scheduler code refactor. 1 year ago
comfyanonymous 446caf711c Sampling code refactor. 1 year ago
comfyanonymous 76cdc809bf Support more controlnet models. 1 year ago
Simon Lui eec449ca8e Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively. 1 year ago
comfyanonymous afa2399f79 Add a way to set output block patches to modify the h and hsp. 1 year ago
comfyanonymous 492db2de8d Allow having a different pooled output for each image in a batch. 1 year ago
comfyanonymous 1cdfb3dba4 Only do the cast on the device if the device supports it. 1 year ago
comfyanonymous 7c9a92f552 Don't depend on torchvision. 1 year ago
MoonRide303 2b6b178173 Added support for lanczos scaling 1 year ago
comfyanonymous b92bf8196e Do lora cast on GPU instead of CPU for higher performance. 1 year ago
comfyanonymous 321c5fa295 Enable pytorch attention by default on xpu. 1 year ago
comfyanonymous 61b1f67734 Support models without previews. 1 year ago
comfyanonymous 43d4935a1d Add cond_or_uncond array to transformer_options so hooks can check what is 1 year ago
comfyanonymous 415abb275f Add DDPM sampler. 1 year ago
comfyanonymous 94e4fe39d8 This isn't used anywhere. 1 year ago
comfyanonymous 44361f6344 Support for text encoder models that need attention_mask. 1 year ago
comfyanonymous 0d8f376446 Set last layer on SD2.x models uses the proper indexes now. 1 year ago
comfyanonymous 0966d3ce82 Don't run text encoders on xpu because there are issues. 1 year ago
comfyanonymous 3039b08eb1 Only parse command line args when main.py is called. 1 year ago
comfyanonymous ed58730658 Don't leave very large hidden states in the clip vision output. 1 year ago
comfyanonymous fb3b728203 Fix issue where autocast fp32 CLIP gave different results from regular. 1 year ago
comfyanonymous 7d401ed1d0 Add ldm format support to UNETLoader. 1 year ago
comfyanonymous e85be36bd2 Add a penultimate_hidden_states to the clip vision output. 1 year ago
comfyanonymous 1e6b67101c Support diffusers format t2i adapters. 1 year ago
comfyanonymous 326577d04c Allow cancelling of everything with a progress bar. 1 year ago
comfyanonymous f88f7f413a Add a ConditioningSetAreaPercentage node. 1 year ago
comfyanonymous 1938f5c5fe Add a force argument to soft_empty_cache to force a cache empty. 1 year ago
Simon Lui 2da73b7073 Revert changes in comfy/ldm/modules/diffusionmodules/util.py, which is unused. 1 year ago
comfyanonymous a74c5dbf37 Move some functions to utils.py 1 year ago
Simon Lui 4a0c4ce4ef Some fixes to generalize CUDA specific functionality to Intel or other GPUs. 1 year ago
comfyanonymous 77a176f9e0 Use common function to reshape batch to. 1 year ago
comfyanonymous 7931ff0fd9 Support SDXL inpaint models. 1 year ago
comfyanonymous 0e3b641172 Remove xformers related print. 1 year ago
comfyanonymous 5c363a9d86 Fix controlnet bug. 1 year ago
comfyanonymous cfe1c54de8 Fix controlnet issue. 1 year ago
comfyanonymous 1c012d69af It doesn't make sense for c_crossattn and c_concat to be lists. 1 year ago
comfyanonymous 7e941f9f24 Clean up DiffusersLoader node. 1 year ago