andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,530 Commits 1 Branch 0 Tags
a562c17e8ac52c6a3cb14902af43dee5a6f1adf4
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
comfyanonymous a562c17e8a load_unet -> load_diffusion_model with a model_options argument. 2024-08-12 23:20:57 -04:00
comfyanonymous 5942c17d55 Order of operations matters. 2024-08-12 21:56:18 -04:00
comfyanonymous b8ffb2937f Memory tweaks. 2024-08-12 15:07:11 -04:00
comfyanonymous 5d43e75e5b Fix some issues with the model sometimes not getting patched. 2024-08-12 12:27:54 -04:00
comfyanonymous 517f4a94e4 Fix some lora loading slowdowns. 2024-08-12 11:50:32 -04:00
comfyanonymous 52a471c5c7 Change name of log. 2024-08-12 10:35:06 -04:00
comfyanonymous ad76574cb8 Fix some potential issues with the previous commits. 2024-08-12 00:23:29 -04:00
comfyanonymous 9acfe4df41 Support loading directly to vram with CLIPLoader node. 2024-08-12 00:06:01 -04:00
comfyanonymous 9829b013ea Fix mistake in last commit. 2024-08-12 00:00:17 -04:00
comfyanonymous 5c69cde037 Load TE model straight to vram if certain conditions are met. 2024-08-11 23:52:43 -04:00
comfyanonymous e9589d6d92 Add a way to set model dtype and ops from load_checkpoint_guess_config. 2024-08-11 08:50:34 -04:00
comfyanonymous 0d82a798a5 Remove the ckpt_path from load_state_dict_guess_config. 2024-08-11 08:37:35 -04:00
comfyanonymous 75b9b55b22 Fix issues with #4302 and support loading diffusers format flux. 2024-08-10 21:28:24 -04:00
comfyanonymous 1de69fe4d5 Fix some issues with inference slowing down. 2024-08-10 16:21:25 -04:00
comfyanonymous ae197f651b Speed up hunyuan dit inference a bit. 2024-08-10 07:36:27 -04:00
comfyanonymous 1b5b8ca81a Fix regression. 2024-08-09 21:45:21 -04:00
comfyanonymous 6678d5cf65 Fix regression. 2024-08-09 14:02:38 -04:00
comfyanonymous a3cc326748 Better fix for lowvram issue. 2024-08-09 12:16:25 -04:00
comfyanonymous 86a97e91fc Fix controlnet regression. 2024-08-09 12:08:58 -04:00
comfyanonymous 5acdadc9f3 Fix issue with some lowvram weights. 2024-08-09 03:58:28 -04:00
comfyanonymous 55ad9d5f8c Fix regression. 2024-08-09 03:36:40 -04:00
comfyanonymous a9f04edc58 Implement text encoder part of HunyuanDiT loras. 2024-08-09 03:21:10 -04:00
comfyanonymous a475ec2300 Cleanup HunyuanDit controlnets. 
Use the: ControlNetApply SD3 and HunyuanDiT node.
 2024-08-09 02:59:34 -04:00
comfyanonymous 413322645e Raw torch is faster than einops? 2024-08-08 22:09:29 -04:00
comfyanonymous 11200de970 Cleaner code. 2024-08-08 20:07:09 -04:00
comfyanonymous 037c38eb0f Try to improve inference speed on some machines. 2024-08-08 17:29:27 -04:00
comfyanonymous 1e11d2d1f5 Better prints. 2024-08-08 17:29:27 -04:00
comfyanonymous 66d4233210 Fix. 2024-08-08 15:16:51 -04:00
comfyanonymous 591010b7ef Support diffusers text attention flux loras. 2024-08-08 14:45:52 -04:00
comfyanonymous 08f92d55e9 Partial model shift support. 2024-08-08 14:45:06 -04:00
comfyanonymous 8115d8cce9 Add Flux fp16 support hack. 2024-08-07 15:08:39 -04:00
comfyanonymous 6969fc9ba4 Make supported_dtypes a priority list. 2024-08-07 15:00:06 -04:00
comfyanonymous cb7c4b4be3 Workaround for lora OOM on lowvram mode. 2024-08-07 14:30:54 -04:00
comfyanonymous 1208863eca Fix "Comfy" lora keys. 
They are in this format now:
diffusion_model.full.model.key.name.lora_up.weight
 2024-08-07 13:49:31 -04:00
comfyanonymous e1c528196e Fix bundled embed. 2024-08-07 13:30:45 -04:00
comfyanonymous 17030fd4c0 Support for "Comfy" lora format. 
The keys are just: model.full.model.key.name.lora_up.weight

It is supported by all comfyui supported models.

Now people can just convert loras to this format instead of having to ask
for me to implement them.
 2024-08-07 13:18:32 -04:00
comfyanonymous c19dcd362f Controlnet code refactor. 2024-08-07 12:59:28 -04:00
comfyanonymous 1c08bf35b4 Support format for embeddings bundled in loras. 2024-08-07 03:45:25 -04:00
comfyanonymous b334605a66 Fix OOMs happening in some cases. 
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
 2024-08-06 13:36:04 -04:00
comfyanonymous de17a9755e Unload all models if there's an OOM error. 2024-08-06 03:30:28 -04:00
comfyanonymous c14ac98fed Unload models and load them back in lowvram mode no free vram. 2024-08-06 03:22:39 -04:00
comfyanonymous 2d75df45e6 Flux tweak memory usage. 2024-08-05 21:58:28 -04:00
comfyanonymous 8edbcf5209 Improve performance on some lowend GPUs. 2024-08-05 16:24:04 -04:00
comfyanonymous e545a636ba This probably doesn't work anymore. 2024-08-05 12:31:42 -04:00
comfyanonymous 78e133d041 Support simple diffusers Flux loras. 2024-08-04 22:05:48 -04:00
comfyanonymous ddb6a9f47c Set the step in EmptySD3LatentImage to 16. 
These models work better when the res is a multiple of 16.
 2024-08-04 15:59:02 -04:00
comfyanonymous 3b71f84b50 ONNX tracing fixes. 2024-08-04 15:45:43 -04:00
comfyanonymous 0a6b008117 Fix issue with some custom nodes. 2024-08-04 10:03:33 -04:00
comfyanonymous 56f3c660bf ModelSamplingFlux now takes a resolution and adjusts the shift with it. 
If you want to sample Flux dev exactly how the reference code does use
the same resolution as your image in this node.
 2024-08-04 04:06:00 -04:00
comfyanonymous f7a5107784 Fix crash. 2024-08-03 16:55:38 -04:00
comfyanonymous 91be9c2867 Tweak lowvram memory formula. 2024-08-03 16:44:50 -04:00
comfyanonymous 03c5018c98 Lower lowvram memory to 1/3 of free memory. 2024-08-03 15:14:07 -04:00
comfyanonymous 2ba5cc8b86 Fix some issues. 2024-08-03 15:06:40 -04:00
comfyanonymous 1e68002b87 Cap lowvram to half of free memory. 2024-08-03 14:50:20 -04:00
comfyanonymous ba9095e5bd Automatically use fp8 for diffusion model weights if: 
Checkpoint contains weights in fp8.

There isn't enough memory to load the diffusion model in GPU vram.
 2024-08-03 13:45:19 -04:00
comfyanonymous f123328b82 Load T5 in fp8 if it's in fp8 in the Flux checkpoint. 2024-08-03 12:39:33 -04:00
comfyanonymous 63a7e8edba More aggressive batch splitting. 2024-08-03 11:53:30 -04:00
comfyanonymous 0eea47d580 Add ModelSamplingFlux to experiment with the shift value. 
Default shift on Flux Schnell is 0.0
 2024-08-03 03:54:38 -04:00
comfyanonymous 7cd0cdfce6 Add advanced model merge node for Flux model. 2024-08-02 23:20:53 -04:00
comfyanonymous ea03c9dcd2 Better per model memory usage estimations. 2024-08-02 18:09:24 -04:00
comfyanonymous 3a9ee995cf Tweak regular SD memory formula. 2024-08-02 17:34:30 -04:00
comfyanonymous 47da42d928 Better Flux vram estimation. 2024-08-02 17:02:35 -04:00
comfyanonymous 17bbd83176 Fix bug loading flac workflow when it contains = character. 2024-08-02 13:14:28 -04:00
comfyanonymous eca962c6da Add FluxGuidance node. 
This lets you adjust the guidance on the dev model which is a parameter
that is passed to the diffusion model.
 2024-08-02 10:25:49 -04:00
comfyanonymous 369f459b20 Fix no longer working on old pytorch. 2024-08-01 22:20:24 -04:00
comfyanonymous e638f2858a Hack to make all resolutions work on Flux models. 2024-08-01 21:39:18 -04:00
comfyanonymous a531001cc7 Add CLIPTextEncodeFlux. 2024-08-01 18:53:25 -04:00
comfyanonymous d420bc792a Tweak the memory usage formulas for Flux and SD. 2024-08-01 17:53:45 -04:00
comfyanonymous d965474aaa Make ComfyUI split batches a higher priority than weight offload. 2024-08-01 16:39:59 -04:00
comfyanonymous 1c61361fd2 Fast preview support for Flux. 2024-08-01 16:28:11 -04:00
comfyanonymous a6decf1e62 Fix bfloat16 potentially not being enabled on mps. 2024-08-01 16:18:44 -04:00
comfyanonymous 48eb1399c0 Try to fix mac issue. 2024-08-01 13:41:27 -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 f2b80f95d2 Better Mac support on flux model. 2024-08-01 13:10:50 -04:00
comfyanonymous 1aa9cf3292 Make lowvram more aggressive on low memory machines. 2024-08-01 12:11:57 -04:00
comfyanonymous 2f88d19ef3 Add link to Flux examples to readme. 2024-08-01 11:48:19 -04:00
comfyanonymous eb96c3bd82 Fix .sft file loading (they are safetensors files). 2024-08-01 11:32:58 -04:00
comfyanonymous 5f98de7697 Load flux t5 in fp8 if weights are in fp8. 2024-08-01 11:05:56 -04:00
comfyanonymous 8d34211a7a Fix old python versions no longer working. 2024-08-01 09:57:20 -04:00
comfyanonymous 1589b58d3e Basic Flux Schnell and Flux Dev model implementation. 2024-08-01 09:49:29 -04:00
comfyanonymous 7ad574bffd Mac supports bf16 just make sure you are using the latest pytorch. 2024-08-01 09:42:17 -04:00
comfyanonymous e2382b6adb Make lowvram less aggressive when there are large amounts of free memory. 2024-08-01 03:58:58 -04:00
comfyanonymous c24f897352 Fix to get fp8 working on T5 base. 2024-07-31 02:00:19 -04:00
comfyanonymous a5991a7aa6 Fix hunyuan dit text encoder weights always being in fp32. 2024-07-31 01:34:57 -04:00
comfyanonymous 2c038ccef0 Lower CLIP memory usage by a bit. 2024-07-31 01:32:35 -04:00
comfyanonymous b85216a3c0 Lower T5 memory usage by a few hundred MB. 2024-07-31 00:52:34 -04:00
comfyanonymous 82cae45d44 Fix potential issue with non clip text embeddings. 2024-07-30 14:41:13 -04:00
comfyanonymous 25853d0be8 Use common function for casting weights to input. 2024-07-30 10:49:14 -04:00
comfyanonymous 79040635da Remove unnecessary code. 2024-07-30 05:01:34 -04:00
comfyanonymous 66d35c07ce Improve artifacts on hydit, auraflow and SD3 on specific resolutions. 
This breaks seeds for resolutions that are not a multiple of 16 in pixel
resolution by using circular padding instead of reflection padding but
should lower the amount of artifacts when doing img2img at those
resolutions.
 2024-07-29 20:48:50 -04:00
comfyanonymous c75b50607b Less confusing exception if pillow() function fails. 2024-07-29 11:15:37 -04:00
comfyanonymous 4ba7fa0244 Refactor: Move sd2_clip.py to text_encoders folder. 2024-07-28 01:19:20 -04:00
comfyanonymous f82d09c9b4 Update packaging workflow. 2024-07-27 04:48:19 -04:00
comfyanonymous e6829e7ac5 Add a way to set custom dependencies in the release workflow. 2024-07-27 04:41:46 -04:00
comfyanonymous 07f6a1a685 Handle case in the updater when master branch is not in local repo. 2024-07-27 03:15:22 -04:00
comfyanonymous e746965c50 Update nightly package workflow. 2024-07-27 01:20:18 -04:00
comfyanonymous 45a2842d7f Set stable releases as a prerelease initially. 
This should give time to test the standalone package before making it live.
 2024-07-26 14:52:20 -04:00
comfyanonymous cf4418b806 Don't treat Bert model like CLIP. 
Bert can accept up to 512 tokens so any prompt with more than 77 should
just be passed to it as is instead of splitting it up like CLIP.
 2024-07-26 13:08:12 -04:00
comfyanonymous 6225a7827c Add CLIPTextEncodeHunyuanDiT. 
Useful for testing what each text encoder does.
 2024-07-26 13:08:06 -04:00