Skip to content
代码片段 群组 项目
选择Git版本
  • add_codeowner
  • add_custom_node_i18n
  • add_kf_interp
  • add_owners
  • add_sample_sigmas
  • add_undefined_lint
  • all_flake
  • base-path-env-var
  • calc_weight_api
  • clean-folder-paths
  • clean_3.8
  • comfyanonymous-patch-1
  • defaultconds_fix
  • desktop-release-feb172025
  • desktop-release-feb192025
  • desktop-release-mar112025
  • document_get_attr
  • explicit_control_option
  • fast_options
  • fix-channels-last-contig-error
  • v0.3.26
  • v0.3.25
  • v0.3.24
  • v0.3.23
  • v0.3.22
  • v0.3.21
  • v0.3.20
  • v0.3.19
  • v0.3.18
  • v0.3.17
  • v0.3.16
  • v0.3.15
  • v0.3.14
  • v0.3.13
  • v0.3.12
  • v0.3.11
  • v0.3.10
  • v0.3.9
  • v0.3.8
  • v0.3.7
40 个结果
可以使用方向键移动图形。
Created with Raphaël 2.2.024Nov232221201918171615141312111098765432131Oct30292827262524232221201918171615141312111098765432130Sep292827262524252423222122212019181716151413141312111098765432131Aug30292827262524232221201918171615141312111098765432131Jul3029282726Skip layer guidance now works on hydit model.Update README.md (#5707)set LTX min length to 1 for t2i (#5750)Skip layer guidance node now works on LTX-Video.Some improvements to the lowvram unloading.Fix some tiled VAE decoding issues with LTX-Video.v0.3.4v0.3.4LTXV lowvram fixes.Some fixes to the lowvram system.v0.3.3v0.3.3Merge branch 'master' into patch_hooks_improved_memoryRemove prints.v0.3.2v0.3.2Remove print.Merge branch 'master' into patch_hooks_improved_memoryAdd LTX-Video support to the Readme.Support Lightricks LTX-Video model.Fix mask issue in some attention functions.Merge branch 'master' into patch_hooks_improved_memoryRevert change, does not workAllow both FLOATS and FLOAT for floats_strength inputOn Cond/Cond Pair nodes, removed opt_ prefix from optional inputsSupport new flux model variants.v0.3.1v0.3.1Add some new weight patching functionality.Update readme.Turn off hook patch caching when only 1 hook present in sampling, replace some current_hook = None with calls to self.patch_hooks(None) instead to avoid a potential edge caseFix mask issue with attention_xformers.Skip layer guidance now works on stable audio model.v0.3.0v0.3.0nitnode_typingnode_typingnitnitShim StrEnumSmall cleanup of comments[Developer Experience] Add node typingMade encode_from_tokens_scheduled work when no hooks are set on patcherRename add_noise_mask -> noise_mask.Add boolean to InpaintModelConditioning to disable the noise mask.Add terminal size fallback (#5623)Refactor inpaint/ip2p code.Removed a .to call on results of calculate_weight in patch_hook_weight_to_device that was screwing up the intermediate results for fp8 prior to being passed into stochastic_rounding callUpdate UI screenshot in README (#5666)For encode_from_tokens_scheduled, allow start_percent and end_percent in add_dict to limit which scheduled conds get encoded for optimization purposesMerge branch 'master' into patch_hooks_improved_memory
加载中