andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,789 Commits 1 Branch 0 Tags
5cbb01bc2f7d4ad27e74c777771f58d468e16649
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
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
comfyanonymous d605677b33 Make euler_ancestral work on flow models (credit: Ashen). 2024-10-25 19:53:44 -04:00
comfyanonymous 52810907e2 Add a model merge node for SD3.5 large. 2024-10-24 16:46:21 -04:00
comfyanonymous 66b0961a46 Fix ControlLora issue with last commit. 2024-10-23 17:02:40 -04:00
comfyanonymous 754597c8a9 Clean up some controlnet code. 
Remove self.device which was useless.
 2024-10-23 14:19:05 -04:00
comfyanonymous 915fdb5745 Fix lowvram edge case. 2024-10-22 16:34:50 -04:00
comfyanonymous 8ce2a1052c Optimizations to --fast and scaled fp8. 2024-10-22 02:12:28 -04:00
comfyanonymous f82314fcfc Fix duplicate sigmas on beta scheduler. 2024-10-21 20:19:45 -04:00
comfyanonymous 0075c6d096 Mixed precision diffusion models with scaled fp8. 
This change allows supports for diffusion models where all the linears are
scaled fp8 while the other weights are the original precision.
 2024-10-21 18:12:51 -04:00
comfyanonymous 83ca891118 Support scaled fp8 t5xxl model. 2024-10-20 22:27:00 -04:00
comfyanonymous f9f9faface Fixed model merging issue with scaled fp8. 2024-10-20 06:24:31 -04:00
comfyanonymous 471cd3eace fp8 casting is fast on GPUs that support fp8 compute. 2024-10-20 00:54:47 -04:00
comfyanonymous a68bbafddb Support diffusion models with scaled fp8 weights. 2024-10-19 23:47:42 -04:00
comfyanonymous 73e3a9e676 Clamp output when rounding weight to prevent Nan. 2024-10-19 19:07:10 -04:00
comfyanonymous 518c0dc2fe Add tooltips to LoraSave node. 2024-10-18 06:01:09 -04:00
comfyanonymous ce0542e10b Add a note that python 3.13 is not yet supported to the README. 2024-10-17 19:27:37 -04:00
comfyanonymous 8473019d40 Pytorch can be shipped with numpy 2 now. 2024-10-17 19:15:17 -04:00
comfyanonymous 67158994a4 Use the lowvram cast_to function for everything. 2024-10-17 17:25:56 -04:00
comfyanonymous 7390ff3b1e Add missing import. 2024-10-16 14:58:30 -04:00
comfyanonymous 0bedfb26af Revert "Fix Transformers FutureWarning (#5140)" 
This reverts commit 95b7cf9bbe.
 2024-10-16 12:36:19 -04:00
comfyanonymous f71cfd2687 Add an experimental node to sharpen latents. 
Can be used with LatentApplyOperationCFG for interesting results.
 2024-10-16 05:25:31 -04:00
comfyanonymous 0dbba9f751 Add some latent operation nodes. 
This is a port of the ModelSamplerTonemapNoiseTest from the experiments
repo.

To replicate that node use LatentOperationTonemapReinhard and
LatentApplyOperationCFG together.
 2024-10-15 15:00:36 -04:00
comfyanonymous f584758271 Cleanup some useless lines. 2024-10-14 21:02:39 -04:00
comfyanonymous 191a0d56b4 Switch default packaging workflows to python 3.12 2024-10-13 06:59:31 -04:00
comfyanonymous 3c60ecd7a8 Fix fp8 ops staying enabled. 2024-10-12 14:10:13 -04:00
comfyanonymous 7ae6626723 Remove useless argument. 2024-10-12 07:16:21 -04:00
comfyanonymous 6632365e16 model_options consistency between functions. 
weight_dtype -> dtype
 2024-10-11 20:51:19 -04:00
comfyanonymous 1b80895285 Make clip loader nodes support loading sd3 t5xxl in lower precision. 
Add attention mask support in the SD3 text encoder code.
 2024-10-10 15:06:15 -04:00
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
comfyanonymous 203942c8b2 Fix flux doras with diffusers keys. 2024-10-08 19:03:40 -04:00
comfyanonymous 8dfa0cc552 Make SD3 fast previews a little better. 2024-10-07 09:19:59 -04:00
comfyanonymous e5ecdfdd2d Make fast previews for SDXL a little better by adding a bias. 2024-10-06 19:27:04 -04:00
comfyanonymous 7d29fbf74b Slightly improve the fast previews for flux by adding a bias. 2024-10-06 17:55:46 -04:00
comfyanonymous 7d2467e830 Some minor cleanups. 2024-10-05 13:22:39 -04:00
comfyanonymous 6f021d8aa0 Let --verbose have an argument for the log level. 2024-10-04 10:05:34 -04:00
comfyanonymous d854ed0bcf Allow using SD3 type te output on flux model. 2024-10-03 09:44:54 -04:00
comfyanonymous abcd006b8c Allow more permutations of clip/t5 in dual clip loader. 2024-10-03 09:26:11 -04:00
comfyanonymous d985d1d7dc CLIP Loader node now supports clip_l and clip_g only for SD3. 2024-10-02 04:25:17 -04:00
comfyanonymous d1cdf51e1b Refactor some of the TE detection code. 2024-10-01 07:08:41 -04:00
comfyanonymous b4626ab93e Add simpletuner lycoris format for SD unet. 2024-09-30 06:03:27 -04:00
comfyanonymous a9e459c2a4 Use torch.nn.functional.linear in RGB preview code. 
Add an optional bias to the latent RGB preview code.
 2024-09-29 11:27:49 -04:00
comfyanonymous 3bb4dec720 Fix issue with loras, lowvram and --fast fp8. 2024-09-28 14:42:32 -04:00
comfyanonymous 83b01f960a Add backend option to TorchCompileModel. 
If you want to use the cudagraphs backend you need to: --disable-cuda-malloc

If you get other backends working feel free to make a PR to add them.
 2024-09-27 02:12:37 -04:00
comfyanonymous d72e871cfa Add a note that the experimental model downloader api will be removed. 2024-09-26 03:17:52 -04:00
comfyanonymous 037c3159b6 Move some nodes out of _for_testing. 2024-09-25 08:41:22 -04:00
comfyanonymous bdd4a22a2e Fix flux TE not loading t5 embeddings. 2024-09-24 22:57:22 -04:00
comfyanonymous fdf37566ef Add batch size to EmptyLatentAudio. 2024-09-24 04:32:55 -04:00
comfyanonymous 3a0eeee320 Make --listen listen on both ipv4 and ipv6 at the same time by default. 2024-09-23 04:38:19 -04:00
comfyanonymous 447da7ea86 Support listening on multiple addresses. 2024-09-23 04:36:59 -04:00
comfyanonymous 9c41bc8d10 Remove useless line. 2024-09-23 02:32:29 -04:00
comfyanonymous 5718ef69bb Add total and free ram to /system_stats. 2024-09-22 03:42:11 -04:00
comfyanonymous 7a415f47a9 Add an optional VAE input to the ControlNetApplyAdvanced node. 
Deprecate the other controlnet nodes.
 2024-09-22 01:24:52 -04:00
comfyanonymous 364b69e931 Make SD3 empty latent image zeros. 
This shouldn't change anything. The reason it was not zeros is because it
did matter in early versions of the code.
 2024-09-21 09:13:10 -04:00
comfyanonymous dc96a1ae19 Load controlnet in fp8 if weights are in fp8. 2024-09-21 04:50:12 -04:00
comfyanonymous 2d810b081e Add load_controlnet_state_dict function. 2024-09-21 01:51:51 -04:00
comfyanonymous 9f7e9f0547 Add an error message when a controlnet needs a VAE but none is given. 2024-09-21 01:33:18 -04:00
comfyanonymous a355f38ecc Make the SD3 controlnet node the default one. 2024-09-21 01:32:46 -04:00
comfyanonymous 70a708d726 Fix model merging issue. 2024-09-20 02:31:44 -04:00
comfyanonymous ad66f7c7d8 Add model_options to load_controlnet function. 2024-09-19 08:23:35 -04:00
comfyanonymous 0bfc7cc998 Create the temp directory on ComfyUI startup instead. 2024-09-18 09:55:57 -04:00
comfyanonymous d514bb38ee Add some option to model_options for the text encoder. 
load_device, offload_device and the initial_device can now be set.
 2024-09-17 03:49:54 -04:00
comfyanonymous 0849c80e2a get_key_patches now works without unloading the model. 2024-09-17 01:57:59 -04:00
comfyanonymous 56e8f5e4fd VAEDecodeAudio now does some normalization on the audio. 2024-09-16 00:30:36 -04:00
comfyanonymous e813abbb2c Long CLIP L support for SDXL, SD3 and Flux. 
Use the *CLIPLoader nodes.
 2024-09-15 07:59:38 -04:00
comfyanonymous ca08597670 Make the inpaint controlnet node work with non inpaint ones. 2024-09-14 09:17:13 -04:00
comfyanonymous f48e390032 Support AliMama SD3 and Flux inpaint controlnets. 
Use the ControlNetInpaintingAliMamaApply node.
 2024-09-14 09:05:16 -04:00
comfyanonymous b3ce8fb9fd Revert "Reduce repeated calls of get_immediate_node_signature for ancestors in cache (#4871)" 
This reverts commit f6b7194f64.
 2024-09-13 23:24:47 -04:00
comfyanonymous cf80d28689 Support loading controlnets with different input. 2024-09-13 09:54:37 -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 9d720187f1 types -> comfy_types to fix import issue. 2024-09-12 03:57:46 -04:00
comfyanonymous 9f4daca9d9 Doesn't really make sense for cfg_pp sampler to call regular one. 2024-09-11 02:51:36 -04:00
comfyanonymous 36c83cdbba Limit origin check to when host is loopback. 
This should still prevent the exploit without breaking things for people
who use reverse proxies.
 2024-09-11 01:06:37 -04:00
comfyanonymous bc94662b31 Cleanup. 2024-09-10 00:43:37 -04:00
comfyanonymous 9a7444e39f Add diffusion_models to the extra_model_paths.yaml.example 2024-09-10 00:21:33 -04:00
comfyanonymous 54fca4a218 If host does not contain a port only compare the hostnames. 2024-09-09 16:28:23 -04:00
comfyanonymous e0b41243b4 Fix issue where sometimes origin doesn't contain the port. 2024-09-09 03:18:17 -04:00
comfyanonymous e3b0402bb7 Ignore origin domain when it's empty. 2024-09-09 01:04:56 -04:00
comfyanonymous cbaac71bf5 Fix issue with last commit. 2024-09-08 19:35:23 -04:00
comfyanonymous 3ab3516e46 By default only accept requests where origin header matches the host. 
Browsers are dumb and let any website do requests to localhost this should
prevent this without breaking things. CORS prevents the javascript from
reading the response but they can still write it.

At the moment this is only enabled when the --enable-cors-header argument
is not used.
 2024-09-08 18:17:29 -04:00
comfyanonymous 9c5fca75f4 Fix lora issue. 2024-09-08 10:10:47 -04:00
comfyanonymous 32a60a7bac Support onetrainer text encoder Flux lora. 2024-09-08 09:31:41 -04:00
comfyanonymous 8aabd7c8c0 SaveLora node can now save "full diff" lora format. 
This isn't actually a lora format and is saving the full diff of the
weights in a format that can be used in the lora loader nodes.
 2024-09-07 03:21:02 -04:00
comfyanonymous a09b29ca11 Add an option to the SaveLora node to store the bias diff. 2024-09-07 03:03:30 -04:00
comfyanonymous 9bfee68773 LoraSave node now supports generating text encoder loras. 
text_encoder_diff should be connected to a CLIPMergeSubtract node.

model_diff and text_encoder_diff are optional inputs so you can create
model only loras, text encoder only loras or a lora that contains both.
 2024-09-07 02:30:12 -04:00
comfyanonymous ea77750759 Support a generic Comfy format for text encoder loras. 
This is a format with keys like:
text_encoders.clip_l.transformer.text_model.encoder.layers.9.self_attn.v_proj.lora_up.weight

Instead of waiting for me to add support for specific lora formats you can
convert your text encoder loras to this format instead.

If you want to see an example save a text encoder lora with the SaveLora
node with the commit right after this one.
 2024-09-07 02:20:39 -04:00
comfyanonymous c27ebeb1c2 Fix onnx export not working on flux. 2024-09-06 03:21:52 -04:00
comfyanonymous dc2eb75b85 Update stable release workflow to latest pytorch with cuda 12.4. 2024-09-05 19:21:52 -04:00
comfyanonymous 5cbaa9e07c Mistoline flux controlnet support. 2024-09-05 00:05:17 -04:00
comfyanonymous c7427375ee Prioritize freeing partially offloaded models first. 2024-09-04 19:47:32 -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
comfyanonymous 483004dd1d Support newer glora format. 2024-09-03 17:02:19 -04:00
comfyanonymous 00a5d08103 Lower fp8 lora memory usage. 2024-09-03 01:25:05 -04:00
comfyanonymous d043997d30 Flux onetrainer lora. 2024-09-02 08:22:15 -04:00
comfyanonymous 8d31a6632f Speed up inference on nvidia 10 series on Linux. 2024-09-01 17:29:31 -04:00
comfyanonymous b643eae08b Make minimum_inference_memory() depend on --reserve-vram 2024-09-01 01:18:34 -04:00
comfyanonymous baa6b4dc36 Update manual install instructions. 2024-08-31 04:37:23 -04:00
comfyanonymous 587e7ca654 Remove github buttons. 2024-08-31 01:53:10 -04:00
comfyanonymous 935ae153e1 Cleanup. 2024-08-30 12:53:59 -04:00