27a0fcccc3
Enable bf16 VAE on RDNA4. ( #9746 )
2025-09-06 23:25:22 -04:00
ea6cdd2631
Print all fast options in --help ( #9737 )
2025-09-06 01:05:05 -04:00
ba3c8e3dbe
Merge branch 'master' into dr-support-pip-cm
2025-09-06 04:05:01 +09:00
2ee7879a0b
Fix lowvram issues with hunyuan3d 2.1 ( #9735 )
2025-09-05 14:57:35 -04:00
fc88b4f939
Merge branch 'master' into dr-support-pip-cm
2025-09-05 18:49:55 +09:00
c9ebe70072
Some changes to the previous hunyuan PR. ( #9725 )
2025-09-04 20:39:02 -04:00
261421e218
Add Hunyuan 3D 2.1 Support ( #8714 )
2025-09-04 20:36:20 -04:00
2ade597d02
Merge branch 'master' into dr-support-pip-cm
2025-09-04 11:55:51 +09:00
72855db715
Fix potential rope issue. ( #9710 )
2025-09-03 22:20:13 -04:00
74a027f589
Merge branch 'master' into dr-support-pip-cm
2025-09-03 12:01:02 +09:00
e3018c2a5a
uso -> uxo/uno as requested. ( #9688 )
2025-09-02 16:12:07 -04:00
3412d53b1d
USO style reference. ( #9677 )
...
Load the projector.safetensors file with the ModelPatchLoader node and use
the siglip_vision_patch14_384.safetensors "clip vision" model and the
USOStyleReferenceNode.
2025-09-02 15:36:22 -04:00
cc21e84115
Merge branch 'master' into dr-support-pip-cm
2025-09-03 00:07:37 +09:00
e2d1e5dad9
Enable Convolution AutoTuning ( #9301 )
2025-09-01 20:33:50 -04:00
27e067ce50
Implement the USO subject identity lora. ( #9674 )
...
Use the lora with FluxContextMultiReferenceLatentMethod node set to "uso"
and a ReferenceLatent node with the reference image.
2025-09-01 18:54:02 -04:00
7fd87423b3
Merge branch 'master' into dr-support-pip-cm
2025-08-31 17:16:00 +09:00
32a627bf1f
SEEDS: update noise decomposition and refactor ( #9633 )
...
- Update the decomposition to reflect interval dependency
- Extract phi computations into functions
- Use torch.lerp for interpolation
2025-08-31 00:01:45 -04:00
1224d58a17
Merge branch 'master' into dr-support-pip-cm
2025-08-30 06:12:16 +09:00
e80a14ad50
Support wan2.2 5B fun control model. ( #9611 )
...
Use the Wan22FunControlToVideo node.
2025-08-28 22:13:07 -04:00
2cc7bafb52
Merge branch 'master' into dr-support-pip-cm
2025-08-29 07:36:57 +09:00
4aa79dbf2c
Adjust flux mem usage factor a bit. ( #9588 )
2025-08-27 23:08:17 -04:00
3aad339b63
Add DPM++ 2M SDE Heun (RES) sampler ( #9542 )
2025-08-27 19:07:31 -04:00
491755325c
Better s2v memory estimation. ( #9584 )
2025-08-27 19:02:42 -04:00
496888fd68
Improve s2v performance when generating videos longer than 120 frames. ( #9582 )
2025-08-27 16:06:40 -04:00
b5ac6ed7ce
Fixes to make controlnet type models work on qwen edit and kontext. ( #9581 )
2025-08-27 15:26:28 -04:00
b20ba1f27c
Fix #9537 ( #9576 )
2025-08-27 12:45:02 -04:00
5c8f724c9a
Merge branch 'master' into dr-support-pip-cm
2025-08-28 00:28:43 +09:00
88aee596a3
WIP Wan 2.2 S2V model. ( #9568 )
2025-08-27 01:10:34 -04:00
eda556d7b4
Merge branch 'dr-support-pip-cm'
2025-08-26 19:45:36 +09:00
914c2a2973
Implement wav2vec2 as an audio encoder model. ( #9549 )
...
This is useless on its own but there are multiple models that use it.
2025-08-25 23:26:47 -04:00
881db45147
Merge branch 'master' into dr-support-pip-cm
2025-08-23 17:46:43 +09:00
41048c69b4
Fix Conditioning masks on 3d latents. ( #9506 )
2025-08-22 23:15:44 -04:00
fc247150fe
Implement EasyCache and Invent LazyCache ( #9496 )
...
* Attempting a universal implementation of EasyCache, starting with flux as test; I screwed up the math a bit, but when I set it just right it works.
* Fixed math to make threshold work as expected, refactored code to use EasyCacheHolder instead of a dict wrapped by object
* Use sigmas from transformer_options instead of timesteps to be compatible with a greater amount of models, make end_percent work
* Make log statement when not skipping useful, preparing for per-cond caching
* Added DIFFUSION_MODEL wrapper around forward function for wan model
* Add subsampling for heuristic inputs
* Add subsampling to output_prev (output_prev_subsampled now)
* Properly consider conds in EasyCache logic
* Created SuperEasyCache to test what happens if caching and reuse is moved outside the scope of conds, added PREDICT_NOISE wrapper to facilitate this test
* Change max reuse_threshold to 3.0
* Mark EasyCache/SuperEasyCache as experimental (beta)
* Make Lumina2 compatible with EasyCache
* Add EasyCache support for Qwen Image
* Fix missing comma, curse you Cursor
* Add EasyCache support to AceStep
* Add EasyCache support to Chroma
* Added EasyCache support to Cosmos Predict t2i
* Make EasyCache not crash with Cosmos Predict ImagToVideo latents, but does not work well at all
* Add EasyCache support to hidream
* Added EasyCache support to hunyuan video
* Added EasyCache support to hunyuan3d
* Added EasyCache support to LTXV (not very good, but does not crash)
* Implemented EasyCache for aura_flow
* Renamed SuperEasyCache to LazyCache, hardcoded subsample_factor to 8 on nodes
* Eatra logging when verbose is true for EasyCache
2025-08-22 22:41:08 -04:00
fe31ad0276
Add elementwise fusions ( #9495 )
...
* Add elementwise fusions
* Add addcmul pattern to Qwen
2025-08-22 19:39:15 -04:00
844e5e7abb
Merge branch 'master' into dr-support-pip-cm
2025-08-22 20:00:27 +09:00
ff57793659
Support InstantX Qwen controlnet. ( #9488 )
2025-08-22 00:53:11 -04:00
20953cbfd4
Merge branch 'master' into dr-support-pip-cm
2025-08-22 12:41:27 +09:00
f7bd5e58dd
Make it easier to implement future qwen controlnets. ( #9485 )
2025-08-21 23:18:04 -04:00
7c36368b14
Merge branch 'master' into dr-support-pip-cm
2025-08-22 05:16:03 +09:00
0963493a9c
Support for Qwen Diffsynth Controlnets canny and depth. ( #9465 )
...
These are not real controlnets but actually a patch on the model so they
will be treated as such.
Put them in the models/model_patches/ folder.
Use the new ModelPatchLoader and QwenImageDiffsynthControlnet nodes.
2025-08-20 22:26:37 -04:00
d7b4f45c5b
Merge branch 'master' into dr-support-pip-cm
2025-08-21 06:44:35 +09:00
8d38ea3bbf
Fix bf16 precision issue with qwen image embeddings. ( #9441 )
2025-08-20 02:58:54 -04:00
5a8f502db5
Disable prompt weights for qwen. ( #9438 )
2025-08-20 01:08:11 -04:00
7cd2c4bd6a
Qwen rotary embeddings should now match reference code. ( #9437 )
2025-08-20 00:45:27 -04:00
4b1aac74bb
Merge branch 'master' into dr-support-pip-cm
2025-08-20 12:25:03 +09:00
dfa791eb4b
Rope fix for qwen vl. ( #9435 )
2025-08-19 20:47:42 -04:00
be456cb37a
Merge branch 'master' into dr-support-pip-cm
2025-08-20 04:02:37 +09:00
4977f203fa
P2 of qwen edit model. ( #9412 )
...
* P2 of qwen edit model.
* Typo.
* Fix normal qwen.
* Fix.
* Make the TextEncodeQwenImageEdit also set the ref latent.
If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
2025-08-18 22:38:34 -04:00
ca04f8f401
Merge branch 'master' into dr-support-pip-cm
2025-08-18 12:23:05 +09:00
7f3b9b16c6
Make step index detection much more robust ( #9392 )
2025-08-17 18:54:07 -04:00
8b44e58e6c
Merge branch 'master' into dr-support-pip-cm
2025-08-18 07:35:15 +09:00
ed43784b0d
WIP Qwen edit model: The diffusion model part. ( #9383 )
2025-08-17 16:45:39 -04:00
0f2b8525bc
Qwen image model refactor. ( #9375 )
2025-08-16 17:51:28 -04:00
1702e6df16
Implement wan2.2 camera model. ( #9357 )
...
Use the old WanCameraImageToVideo node.
2025-08-15 17:29:58 -04:00
c308a8840a
Add FluxKontextMultiReferenceLatentMethod node. ( #9356 )
...
This node is only useful if someone trains the kontext model to properly
use multiple reference images via the index method.
The default is the offset method which feeds the multiple images like if
they were stitched together as one. This method works with the current
flux kontext model.
2025-08-15 15:50:39 -04:00
e08ecfbd8a
Add warning when using old pytorch. ( #9347 )
2025-08-15 00:22:26 -04:00
4e5c230f6a
Fix last commit not working on older pytorch. ( #9346 )
2025-08-14 23:44:02 -04:00
f0d5d0111f
Avoid torch compile graphbreak for older pytorch versions ( #9344 )
...
Turns out torch.compile has some gaps in context manager decorator
syntax support. I've sent patches to fix that in PyTorch, but it won't
be available for all the folks running older versions of PyTorch, hence
this trivial patch.
2025-08-14 23:41:37 -04:00
ad19a069f6
Make SLG nodes work on Qwen Image model. ( #9345 )
2025-08-14 23:16:01 -04:00
91555acf2c
Merge branch 'master' into dr-support-pip-cm
2025-08-14 12:01:56 +09:00
e4f7ea105f
Added context window support to core sampling code ( #9238 )
...
* Added initial support for basic context windows - in progress
* Add prepare_sampling wrapper for context window to more accurately estimate latent memory requirements, fixed merging wrappers/callbacks dicts in prepare_model_patcher
* Made context windows compatible with different dimensions; works for WAN, but results are bad
* Fix comfy.patcher_extension.merge_nested_dicts calls in prepare_model_patcher in sampler_helpers.py
* Considering adding some callbacks to context window code to allow extensions of behavior without the need to rewrite code
* Made dim slicing cleaner
* Add Wan Context WIndows node for testing
* Made context schedule and fuse method functions be stored on the handler instead of needing to be registered in core code to be found
* Moved some code around between node_context_windows.py and context_windows.py
* Change manual context window nodes names/ids
* Added callbacks to IndexListContexHandler
* Adjusted default values for context_length and context_overlap, made schema.inputs definition for WAN Context Windows less annoying
* Make get_resized_cond more robust for various dim sizes
* Fix typo
* Another small fix
2025-08-13 21:33:05 -04:00
c991a5da65
Fix XPU iGPU regressions ( #9322 )
...
* Change bf16 check and switch non-blocking to off default with option to force to regain speed on certain classes of iGPUs and refactor xpu check.
* Turn non_blocking off by default for xpu.
* Update README.md for Intel GPUs.
2025-08-13 19:13:35 -04:00
9df8792d4b
Make last PR not crash comfy on old pytorch. ( #9324 )
2025-08-13 15:12:41 -04:00
3da5a07510
SDPA backend priority ( #9299 )
2025-08-13 14:53:27 -04:00
d7777dc83a
Merge branch 'master' into dr-support-pip-cm
2025-08-14 02:36:19 +09:00
560d38f34c
Wan2.2 fun control support. ( #9292 )
2025-08-12 23:26:33 -04:00
264116dc4d
Merge branch 'master' into dr-support-pip-cm
2025-08-12 10:13:31 +09:00
2208aa616d
Support SimpleTuner lycoris lora for Qwen-Image ( #9280 )
2025-08-11 16:56:16 -04:00
37277e4188
Merge branch 'master' into dr-support-pip-cm
2025-08-10 20:57:20 +09:00
5828607ccf
Not sure if AMD actually support fp16 acc but it doesn't crash. ( #9258 )
2025-08-09 12:49:25 -04:00
106510197a
Merge branch 'master' into dr-support-pip-cm
2025-08-08 23:48:53 +09:00
735bb4bdb1
Users report gfx1201 is buggy on flux with pytorch attention. ( #9244 )
2025-08-08 04:21:00 -04:00
2fe58571e2
Merge branch 'master' into dr-support-pip-cm
2025-08-07 07:45:14 +09:00
4c3e57b0ae
Fixed an issue where qwenLora could not be loaded properly. ( #9208 )
2025-08-06 13:23:11 -04:00
d044a24398
Fix default shift and any latent size for qwen image model. ( #9186 )
2025-08-05 06:12:27 -04:00
46209599ff
Merge branch 'master' into dr-support-pip-cm
2025-08-05 12:24:25 +09:00
c012400240
Initial support for qwen image model. ( #9179 )
2025-08-04 22:53:25 -04:00
02317a1f71
Merge branch 'master' into dr-support-pip-cm
2025-08-05 06:21:27 +09:00
03895dea7c
Fix another issue with the PR. ( #9170 )
2025-08-04 04:33:04 -04:00
84f9759424
Add some warnings and prevent crash when cond devices don't match. ( #9169 )
2025-08-04 04:20:12 -04:00
7991341e89
Various fixes for broken things from earlier PR. ( #9168 )
2025-08-04 04:02:40 -04:00
140ffc7fdc
Fix broken controlnet from last PR. ( #9167 )
2025-08-04 03:28:12 -04:00
182f90b5ec
Lower cond vram use by casting at the same time as device transfer. ( #9159 )
2025-08-04 03:11:53 -04:00
ac7e83448e
Merge branch 'master' into dr-support-pip-cm
2025-08-04 07:25:20 +09:00
aebac22193
Cleanup. ( #9160 )
2025-08-03 07:08:11 -04:00
13aaa66ec2
Make sure context is on the right device. ( #9154 )
2025-08-02 15:09:23 -04:00
5f582a9757
Make sure all the conds are on the right device. ( #9151 )
2025-08-02 15:00:13 -04:00
1e638a140b
Tiny wan vae optimizations. ( #9136 )
2025-08-01 05:25:38 -04:00
5582e2a0f3
Merge branch 'master' into dr-support-pip-cm
2025-07-31 12:33:38 +09:00
61b08d4ba6
Replace manual x * sigmoid(x) with torch silu in VAE nonlinearity ( #9057 )
2025-07-30 19:25:56 -04:00
da9dab7edd
Small wan camera memory optimization. ( #9111 )
2025-07-30 05:55:26 -04:00
3c8196a170
Merge branch 'master' into dr-support-pip-cm
2025-07-30 12:14:34 +09:00
dca6bdd4fa
Make wan2.2 5B i2v take a lot less memory. ( #9102 )
2025-07-29 19:44:18 -04:00
62c08e4659
Merge branch 'master' into dr-support-pip-cm
2025-07-29 23:44:44 +09:00
7d593baf91
Extra reserved vram on large cards on windows. ( #9093 )
2025-07-29 04:07:45 -04:00
ac7bde1d03
Merge branch 'master' into dr-support-pip-cm
2025-07-29 12:13:25 +09:00
c60dc4177c
Remove unecessary clones in the wan2.2 VAE. ( #9083 )
2025-07-28 14:48:19 -04:00
a88788dce6
Wan 2.2 support. ( #9080 )
2025-07-28 08:00:23 -04:00
6909638a42
Merge branch 'master' into dr-support-pip-cm
2025-07-27 15:01:02 +09:00
0621d73a9c
Remove useless code. ( #9059 )
2025-07-26 04:44:19 -04:00
d0625d7f7c
Merge branch 'master' into dr-support-pip-cm
2025-07-26 09:35:21 +09:00
e6e5d33b35
Remove useless code. ( #9041 )
...
This is only needed on old pytorch 2.0 and older.
2025-07-25 04:58:28 -04:00
6b19857c93
Merge branch 'master' into dr-support-pip-cm
2025-07-25 12:21:17 +09:00
4293e4da21
Add WAN ATI support ( #8874 )
...
* Add WAN ATI support
* Fixes
* Fix length
* Remove extra functions
* Fix
* Fix
* Ruff fix
* Remove torch.no_grad
* Add batch trajectory logic
* Scale inputs before and after motion patch
* Batch image/trajectory
* Ruff fix
* Clean up
2025-07-24 20:59:19 -04:00
69cb57b342
Print xpu device name. ( #9035 )
2025-07-24 15:06:25 -04:00
0ccc88b03f
Support Iluvatar CoreX ( #8585 )
...
* Support Iluvatar CoreX
Co-authored-by: mingjiang.li <mingjiang.li@iluvatar.com>
2025-07-24 13:57:36 -04:00
4e904305ce
Merge branch 'dr-support-pip-cm'
2025-07-24 12:22:50 +09:00
eb2f78b4e0
[Training Node] algo support, grad acc, optional grad ckpt ( #9015 )
...
* Add factorization utils for lokr
* Add lokr train impl
* Add loha train impl
* Add adapter map for algo selection
* Add optional grad ckpt and algo selection
* Update __init__.py
* correct key name for loha
* Use custom fwd/bwd func and better init for loha
* Support gradient accumulation
* Fix bugs of loha
* use more stable init
* Add OFT training
* linting
2025-07-23 20:57:27 -04:00
e729a5cc11
Separate denoised and noise estimation in Euler CFG++ ( #9008 )
...
This will change their behavior with the sampling CONST type.
It also combines euler_cfg_pp and euler_ancestral_cfg_pp into one main function.
2025-07-23 19:47:05 -04:00
d3504e1778
Enable pytorch attention by default for gfx1201 on torch 2.8 ( #9029 )
2025-07-23 19:21:29 -04:00
a86a58c308
Fix xpu function not implemented p2. ( #9027 )
2025-07-23 18:18:20 -04:00
39dda1d40d
Fix xpu function not implemented. ( #9026 )
2025-07-23 18:10:59 -04:00
5ad33787de
Add default device argument. ( #9023 )
2025-07-23 14:20:49 -04:00
726aa75126
Merge branch 'master' into dr-support-pip-cm
2025-07-23 12:57:43 +09:00
255f139863
Add xpu version for async offload and some other things. ( #9004 )
2025-07-22 15:20:09 -04:00
3c9a0fcf8a
Merge branch 'master' into dr-support-pip-cm
2025-07-17 12:23:03 +09:00
491fafbd64
Silence clip tokenizer warning. ( #8934 )
2025-07-16 14:42:07 -04:00
9bc2798f72
LTXV VAE decoder: switch default padding mode ( #8930 )
2025-07-16 13:54:38 -04:00
50afba747c
Add attempt to work around the safetensors mmap issue. ( #8928 )
2025-07-16 03:42:17 -04:00
0adeb9b135
Merge branch 'master' into dr-support-pip-cm
2025-07-15 12:02:07 +09:00
543c24108c
Fix wrong reference bug ( #8910 )
2025-07-14 20:45:55 -04:00
98b5183ed8
Merge branch 'master' into dr-support-pip-cm
2025-07-15 06:46:20 +09:00
b40143984c
Add model detection error hint for lora. ( #8880 )
2025-07-12 03:49:26 -04:00
16a0b24da4
Merge branch 'master' into dr-support-pip-cm
2025-07-12 09:19:32 +09:00
938d3e8216
Remove windows line endings. ( #8866 )
2025-07-11 02:37:51 -04:00
2b653e8c18
Support for async node functions ( #8830 )
...
* Support for async execution functions
This commit adds support for node execution functions defined as async. When
a node's execution function is defined as async, we can continue
executing other nodes while it is processing.
Standard uses of `await` should "just work", but people will still have
to be careful if they spawn actual threads. Because torch doesn't really
have async/await versions of functions, this won't particularly help
with most locally-executing nodes, but it does work for e.g. web
requests to other machines.
In addition to the execute function, the `VALIDATE_INPUTS` and
`check_lazy_status` functions can also be defined as async, though we'll
only resolve one node at a time right now for those.
* Add the execution model tests to CI
* Add a missing file
It looks like this got caught by .gitignore? There's probably a better
place to put it, but I'm not sure what that is.
* Add the websocket library for automated tests
* Add additional tests for async error cases
Also fixes one bug that was found when an async function throws an error
after being scheduled on a task.
* Add a feature flags message to reduce bandwidth
We now only send 1 preview message of the latest type the client can
support.
We'll add a console warning when the client fails to send a feature
flags message at some point in the future.
* Add async tests to CI
* Don't actually add new tests in this PR
Will do it in a separate PR
* Resolve unit test in GPU-less runner
* Just remove the tests that GHA can't handle
* Change line endings to UNIX-style
* Avoid loading model_management.py so early
Because model_management.py has a top-level `logging.info`, we have to
be careful not to import that file before we call `setup_logging`. If we
do, we end up having the default logging handler registered in addition
to our custom one.
2025-07-10 14:46:19 -04:00
aac10ad23a
Add SA-Solver sampler ( #8834 )
2025-07-08 16:17:06 -04:00
974254218a
Un-hardcode chroma patch_size ( #8840 )
2025-07-08 15:56:59 -04:00
552fe9df02
Merge branch 'master' into dr-support-pip-cm
2025-07-08 12:34:29 +09:00
75d327abd5
Remove some useless code. ( #8812 )
2025-07-06 07:07:39 -04:00
ee615ac269
Add warning when loading file unsafely. ( #8800 )
2025-07-05 14:34:57 -04:00
f41f323c52
Add the denoising step to several samplers ( #8780 )
2025-07-03 19:20:53 -04:00
2ce64b131c
Merge branch 'master' into dr-support-pip-cm
2025-07-04 06:35:21 +09:00
d9277301d2
Initial code for new SLG node ( #8759 )
2025-07-02 20:13:43 -04:00
111f583e00
Fallback to regular op when fp8 op throws exception. ( #8761 )
2025-07-02 00:57:13 -04:00
d6fa7a7c84
Merge branch 'master' into dr-support-pip-cm
2025-07-02 12:03:03 +09:00
b22e97dcfa
Migrate ER-SDE from VE to VP algorithm and add its sampler node ( #8744 )
...
Apply alpha scaling in the algorithm for reverse-time SDE and add custom ER-SDE sampler node for other solver types (SDE, ODE).
2025-07-01 02:38:52 -04:00
ad633b2953
Merge branch 'master' into dr-support-pip-cm
2025-07-01 12:55:47 +09:00
170c7bb90c
Fix contiguous issue with pytorch nightly. ( #8729 )
2025-06-29 06:38:40 -04:00
9eba1547f4
Merge branch 'master' into dr-support-pip-cm
2025-06-29 15:31:19 +09:00
396454fa41
Reorder the schedulers so simple is the default one. ( #8722 )
2025-06-28 18:12:56 -04:00
ba9548f756
“--whitelist-custom-nodes” args for comfy core to go with “--disable-all-custom-nodes” for development purposes ( #8592 )
...
* feat: “--whitelist-custom-nodes” args for comfy core to go with “--disable-all-custom-nodes” for development purposes
* feat: Simplify custom nodes whitelist logic to use consistent code paths
2025-06-28 15:24:02 -04:00
f398256d11
Merge branch 'master' into dr-support-pip-cm
2025-06-28 10:53:05 +09:00
c36be0ea09
Fix memory estimation bug with kontext. ( #8709 )
2025-06-27 17:21:12 -04:00
9093301a49
Don't add tiny bit of random noise when VAE encoding. ( #8705 )
...
Shouldn't change outputs but might make things a tiny bit more
deterministic.
2025-06-27 14:14:56 -04:00
8744ebb4a1
Merge branch 'master' into dr-support-pip-cm
2025-06-27 07:34:33 +09:00
ef5266b1c1
Support Flux Kontext Dev model. ( #8679 )
2025-06-26 11:28:41 -04:00
a96e65df18
Disable omnigen2 fp16 on older pytorch versions. ( #8672 )
2025-06-26 03:39:09 -04:00
d5167d2ded
Merge branch 'master' into dr-support-pip-cm
2025-06-26 08:59:09 +09:00
ec70ed6aea
Omnigen2 model implementation. ( #8669 )
2025-06-25 19:35:57 -04:00
7a13f74220
unet -> diffusion model ( #8659 )
2025-06-25 04:52:34 -04:00
8042eb20c6
Singlestep DPM++ SDE for RF ( #8627 )
...
Refactor the algorithm, and apply alpha scaling.
2025-06-24 14:59:09 -04:00
39f39c3aa9
Merge branch 'master' into dr-support-pip-cm
2025-06-21 23:51:13 +09:00
1883e70b43
Fix exception when using a noise mask with cosmos predict2. ( #8621 )
...
* Fix exception when using a noise mask with cosmos predict2.
* Fix ruff.
2025-06-21 03:30:39 -04:00
4e95c0c104
Merge branch 'master' into dr-support-pip-cm
2025-06-20 22:12:07 +09:00
f7fb193712
Small flux optimization. ( #8611 )
2025-06-20 05:37:32 -04:00
7e9267fa77
Make flux controlnet work with sd3 text enc. ( #8599 )
2025-06-19 18:50:05 -04:00
91d40086db
Fix pytorch warning. ( #8593 )
2025-06-19 11:04:52 -04:00
8e81c507d2
Multistep DPM++ SDE samplers for RF ( #8541 )
...
Include alpha in sampling and minor refactoring
2025-06-16 14:47:10 -04:00
e1c6dc720e
Allow setting min_length with tokenizer_data. ( #8547 )
2025-06-16 13:43:52 -04:00
d1ab6adc3a
Merge branch 'master' into dr-support-pip-cm
2025-06-16 06:38:35 +09:00
7ea79ebb9d
Add correct eps to ltxv rmsnorm. ( #8542 )
2025-06-15 12:21:25 -04:00
d6a2137fc3
Support Cosmos predict2 image to video models. ( #8535 )
...
Use the CosmosPredict2ImageToVideoLatent node.
2025-06-14 21:37:07 -04:00
53e8d8193c
Generalize SEEDS samplers ( #8529 )
...
Restore VP algorithm for RF and refactor noise_coeffs and half-logSNR calculations
2025-06-14 16:58:16 -04:00
29596bd53f
Small cosmos attention code refactor. ( #8530 )
2025-06-14 05:02:05 -04:00
520eb77b72
LoRA Trainer: LoRA training node in weight adapter scheme ( #8446 )
2025-06-13 19:25:59 -04:00
c69af655aa
Uncap cosmos predict2 res and fix mem estimation. ( #8518 )
2025-06-13 07:30:18 -04:00
251f54a2ad
Basic initial support for cosmos predict2 text to image 2B and 14B models. ( #8517 )
2025-06-13 07:05:23 -04:00
50c605e957
Add support for sqlite database ( #8444 )
...
* Add support for sqlite database
* fix
2025-06-11 16:43:39 -04:00
8a4ff747bd
Fix mistake in last commit. ( #8496 )
...
* Move to right place.
2025-06-11 15:13:29 -04:00
af1eb58be8
Fix black images on some flux models in fp16. ( #8495 )
2025-06-11 15:09:11 -04:00
6e28a46454
Apple most likely is never fixing the fp16 attention bug. ( #8485 )
2025-06-10 13:06:24 -04:00
7f800d04fa
Enable AMD fp8 and pytorch attention on some GPUs. ( #8474 )
...
Information is from the pytorch source code.
2025-06-09 12:50:39 -04:00
35a294431f
Merge branch 'master' into dr-support-pip-cm
2025-06-09 12:34:23 +09:00
97755eed46
Enable fp8 ops by default on gfx1201 ( #8464 )
2025-06-08 14:15:34 -04:00
daf9d25ee2
Cleaner torch version comparisons. ( #8453 )
2025-06-07 10:01:15 -04:00
3b4b171e18
Alternate fix for #8435 ( #8442 )
2025-06-06 09:43:27 -04:00
4248b1618f
Let chroma TE work on regular flux. ( #8429 )
2025-06-05 10:07:17 -04:00
fb4754624d
Make the casting in lists the same as regular inputs. ( #8373 )
2025-06-01 05:39:54 -04:00
19e45e9b0e
Make it easier to pass lists of tensors to models. ( #8358 )
2025-05-31 20:00:20 -04:00
baeeeb02b9
Merge branch 'master' into dr-support-pip-cm
2025-06-01 04:34:00 +09:00
08b7cc7506
use fused multiply-add pointwise ops in chroma ( #8279 )
2025-05-30 18:09:54 -04:00
704fc78854
Put ROCm version in tuple to make it easier to enable stuff based on it. ( #8348 )
2025-05-30 15:41:02 -04:00
f2289a1f59
Delete useless file. ( #8327 )
2025-05-29 08:29:37 -04:00
5e5e46d40c
Not really tested WAN Phantom Support. ( #8321 )
2025-05-28 23:46:15 -04:00
1c1687ab1c
Support HiDream SimpleTuner loras. ( #8318 )
2025-05-28 18:47:15 -04:00
06c661004e
Memory estimation code can now take into account conds. ( #8307 )
2025-05-27 15:09:05 -04:00
89a84e32d2
Disable initial GPU load when novram is used. ( #8294 )
2025-05-26 16:39:27 -04:00
e5799c4899
Enable pytorch attention by default on AMD gfx1151 ( #8282 )
2025-05-26 04:29:25 -04:00
ef641f3e4b
Merge branch 'master' into dr-support-pip-cm
2025-05-26 02:23:34 +09:00
a0651359d7
Return proper error if diffusion model not detected properly. ( #8272 )
2025-05-25 05:28:11 -04:00
5a87757ef9
Better error if sageattention is installed but a dependency is missing. ( #8264 )
2025-05-24 06:43:12 -04:00
0b50d4c0db
Add argument to explicitly enable fp8 compute support. ( #8257 )
...
This can be used to test if your current GPU/pytorch version supports fp8 matrix mult in combination with --fast or the fp8_e4m3fn_fast dtype.
2025-05-23 17:43:50 -04:00
30b2eb8a93
create arange on-device ( #8255 )
2025-05-23 16:15:06 -04:00
f85c08df06
Make VACE conditionings stackable. ( #8240 )
2025-05-22 19:22:26 -04:00
87f9130778
Revert "This doesn't seem to be needed on chroma. ( #8209 )" ( #8210 )
...
This reverts commit 7e84bf5373
2025-05-20 05:39:55 -04:00
7e84bf5373
This doesn't seem to be needed on chroma. ( #8209 )
2025-05-20 05:29:23 -04:00
9ac185456f
Merge branch 'master' into dr-support-pip-cm
2025-05-19 06:04:10 +09:00
aee2908d03
Remove useless log. ( #8166 )
2025-05-17 06:27:34 -04:00
1c2d45d2b5
Fix typo in last PR. ( #8144 )
...
More robust model detection for future proofing.
2025-05-15 19:02:19 -04:00
comfyanonymous
Dr.Lt.Data
Yousef R. Gamaleldin
contentis
chaObserv
Gangin Park
Kohaku-Blueleaf
Jedrzej Kosinski
Xiangxi Guo (Ryan)
Simon Lui
PsychoLogicAu
flybirdxx
Eugene Fairley
honglyua
Harel Cain
Yoland Yan
guill
josephrocca
City
xufeng
pythongosssss
drhead