Jedrzej Kosinski
a54e734ea7
Cleaned up text encode nodes with just a single clip.encode_from_tokens_scheduled call
2024-11-27 21:35:41 -06:00
Jedrzej Kosinski
26ccd3b5f9
Merge branch 'master' into patch_hooks_improved_memory
2024-11-24 15:46:25 -06:00
comfyanonymous
6e8cdcd3cb
Fix some tiled VAE decoding issues with LTX-Video.
2024-11-22 18:00:34 -05:00
Jedrzej Kosinski
0a432c1a73
Merge branch 'master' into patch_hooks_improved_memory
2024-11-22 09:33:13 -06:00
comfyanonymous
5e16f1d24b
Support Lightricks LTX-Video model.
2024-11-22 08:46:39 -05:00
Jedrzej Kosinski
76b9ed1f2d
Merge branch 'master' into patch_hooks_improved_memory
2024-11-21 17:46:25 -06:00
comfyanonymous
898615122f
Rename add_noise_mask -> noise_mask.
2024-11-19 15:31:09 -05:00
comfyanonymous
156a28786b
Add boolean to InpaintModelConditioning to disable the noise mask.
2024-11-19 07:31:29 -05:00
Jedrzej Kosinski
365170af95
Merge branch 'master' into patch_hooks_improved_memory
2024-11-18 08:43:19 -06:00
comfyanonymous
9a0a5d32ee
Add a skip layer guidance node that can also skip single layers.
...
This one should work for skipping the single layers of models like Flux
and Auraflow.
If you want to see how these models work and how many double/single layers
they have see the "ModelMerge*" nodes for the specific model.
2024-11-18 02:20:43 -05:00
Jedrzej Kosinski
4195dfb032
Merge branch 'master' into patch_hooks_improved_memory
2024-11-11 11:26:27 -06:00
Dr.Lt.Data
2d28b0b479
improve: add descriptions for clip loaders ( #5576 )
2024-11-11 05:37:23 -05:00
comfyanonymous
8a5281006f
Fix some custom nodes.
2024-11-10 22:41:00 -05:00
comfyanonymous
b49616f951
Make VAEDecodeTiled node work with video VAEs.
2024-11-07 03:47:12 -05:00
comfyanonymous
ee8abf0cff
Update folder paths: "clip" -> "text_encoders"
...
You can still use models/clip but the folder might get removed eventually
on new installs of ComfyUI.
2024-11-02 15:35:38 -04:00
Jedrzej Kosinski
16735c98e0
Make encode_from_tokens_scheduled call cleaner, rollback change in model_patcher.py for hook_patches_backup dict
2024-11-01 02:01:45 -05:00
Jedrzej Kosinski
3bcbcce88d
Merge branch 'master' into patch_hooks
2024-10-31 18:34:05 -05:00
Uriel Deveaud
cc9cf6d1bd
Rename some nodes in Display Name Mappings (nodes.py) ( #5439 )
...
* Update nodes_images.py
Nodes menu has inconsistency in names, some with spaces between words, other not.
* Update nodes.py
Include the node mapping name line for Image Crop Node
* Update nodes_images.py
* Rename image nodes
add space between words for consistency > Display name mappings
2024-10-31 15:18:05 -04:00
Uriel Deveaud
f2aaa0a475
Rename ImageCrop to Image Crop ( #5424 )
...
* Update nodes_images.py
Nodes menu has inconsistency in names, some with spaces between words, other not.
* Update nodes.py
Include the node mapping name line for Image Crop Node
* Update nodes_images.py
2024-10-31 00:35:34 -04:00
Jedrzej Kosinski
d5169df808
Added initial support within CLIP Text Encode (Prompt) node for scheduling weight hook CLIP strength via clip_start_percent/clip_end_percent on conds, added schedule_clip toggle to Set CLIP Hooks node, small cleanup/fixes
2024-10-30 04:56:09 -05:00
comfyanonymous
5cbb01bc2f
Basic Genmo Mochi video model support.
...
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.
EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
2024-10-26 06:54:00 -04:00
comfyanonymous
c3ffbae067
Make LatentUpscale nodes work on 3d latents.
2024-10-26 01:50:51 -04:00
Jedrzej Kosinski
4bbdf2bfe5
Merge branch 'master' into patch_hooks
2024-10-23 21:10:46 -05:00
comfyanonymous
e38c94228b
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
...
This is used to load weights in fp8 and use fp8 matrix multiplication.
2024-10-09 19:43:17 -04:00
Jedrzej Kosinski
06fbdb03ef
Merge branch 'master' into patch_hooks
2024-10-05 06:43:43 -05:00
comfyanonymous
7a415f47a9
Add an optional VAE input to the ControlNetApplyAdvanced node.
...
Deprecate the other controlnet nodes.
2024-09-22 01:24:52 -04:00
kosinkadink1@gmail.com
a154d0df23
Merge branch 'master' into patch_hooks
2024-09-22 11:54:55 +09:00
comfyanonymous
a355f38ecc
Make the SD3 controlnet node the default one.
2024-09-21 01:32:46 -04:00
Alex "mcmonkey" Goodwin
254838f23c
add simple error check to model loading ( #4950 )
2024-09-17 03:57:17 -04:00
kosinkadink1@gmail.com
6b14fc8795
Merge branch 'master' into patch_hooks
2024-09-17 15:31:03 +09:00
kosinkadink1@gmail.com
9ded65a616
Added initial set of hook-related nodes, added code to register hooks for loras/model-as-loras, small renaming/refactoring
2024-09-15 08:33:17 +09:00
comfyanonymous
f48e390032
Support AliMama SD3 and Flux inpaint controlnets.
...
Use the ControlNetInpaintingAliMamaApply node.
2024-09-14 09:05:16 -04:00
comfyanonymous
7c6eb4fb29
Set some nodes as DEPRECATED.
2024-09-12 20:27:07 -04:00
comfyanonymous
d0b7ab88ba
Add a simple experimental TorchCompileModel node.
...
It probably only works on Linux.
For maximum speed on Flux with Nvidia 40 series/ada and newer try using
this node with fp8_e4m3fn and the --fast argument.
2024-09-12 05:24:25 -04:00
comfyanonymous
22d1241a50
Add an experimental LoraSave node to extract model loras.
...
The model_diff input should be connected to the output of a
ModelMergeSubtract node.
2024-09-04 16:38:38 -04:00
Vedat Baday
04278afb10
feat: return import_failed from init_extra_nodes function ( #4694 )
2024-08-30 19:26:47 -04:00
comfyanonymous
4f7a3cb6fb
unet -> diffusion_models.
2024-08-17 21:31:04 -04:00
Matthew Turnshek
1770fc77ed
Implement support for taef1 latent previews ( #4409 )
...
* add taef1 handling to several places
* remove guess_latent_channels and add latent_channels info directly to flux model
* remove TODO
* fix numbers
2024-08-16 12:53:13 -04:00
pythongosssss
e60e19b175
Add support for simple tooltips ( #3842 )
...
* Add support for simple tooltips
* Fix overflow
* Add tooltips for nodes in the default workflow
* new line
* Prevent potential crash
* PR feedback
* Hide tooltip when clicking (e.g. combo widget)
* Refactor tooltips, add node level support
* Fix
* move
* Fix test (and undo last change)
* Fixed indent
* Fix dom widgets, dont show tooltip if not over canvas
2024-08-14 01:22:10 -04:00
comfyanonymous
a562c17e8a
load_unet -> load_diffusion_model with a model_options argument.
2024-08-12 23:20:57 -04:00
comfyanonymous
369f459b20
Fix no longer working on old pytorch.
2024-08-01 22:20:24 -04:00
comfyanonymous
a531001cc7
Add CLIPTextEncodeFlux.
2024-08-01 18:53:25 -04:00
comfyanonymous
b4f6ebb2e8
Rename UNETLoader node to "Load Diffusion Model".
2024-08-01 13:33:30 -04:00
comfyanonymous
d7430a1651
Add a way to load the diffusion model in fp8 with UNETLoader node.
2024-08-01 13:30:51 -04:00
comfyanonymous
1589b58d3e
Basic Flux Schnell and Flux Dev model implementation.
2024-08-01 09:49:29 -04:00
comfyanonymous
6225a7827c
Add CLIPTextEncodeHunyuanDiT.
...
Useful for testing what each text encoder does.
2024-07-26 13:08:06 -04:00
comfyanonymous
60383f3b64
Move controlnet nodes to conditioning/controlnet.
2024-07-16 17:08:25 -04:00
comfyanonymous
8270c62530
Add SetUnionControlNetType to set the type of the union controlnet model.
2024-07-16 17:04:53 -04:00
comfyanonymous
33346fd9b8
Fix bug with custom nodes on other drives.
2024-07-15 20:38:26 -04:00
comfyanonymous
391c1046cf
More flexibility with text encoder return values.
...
Text encoders can now return other values to the CONDITIONING than the cond
and pooled output.
2024-07-10 20:06:50 -04:00
