1a0486bb96
Fix model needing to be loaded on GPU to generate the sigmas.
8 months ago
1f8d8e6c77
Add InstructPixToPixConditioning node.
8 months ago
5272fd4b03
Add DualCFGGuider used in IP2P models for example.
8 months ago
cfbf3be54b
Add basic guider for models with no cfg.
8 months ago
c6bd456c45
Make zero denoise a NOP.
8 months ago
fcfd2bdf8a
Small cleanup.
8 months ago
f117566299
SamplerCustomAdvanced node.
...
This node enables the creation of nodes to change the guider/denoiser and
the noise algorithm.
8 months ago
0542088ef8
Refactor sampler code for more advanced sampler nodes part 2.
8 months ago
57753c964a
Refactor sampling code for more advanced sampler nodes.
8 months ago
6c6a39251f
Fix saving text encoder in fp8.
8 months ago
e6482fbbfc
Refactor calc_cond_uncond_batch into calc_cond_batch.
...
calc_cond_batch can take an arbitrary amount of cond inputs.
Added a calc_cond_uncond_batch wrapper with a warning so custom nodes
won't break.
8 months ago
1306464538
--force-fp16 is no longer necessary on Mac.
8 months ago
575acb69e4
IP2P model loading support.
...
This is the code to load the model and inference it with only a text
prompt. This commit does not contain the nodes to properly use it with an
image input.
This supports both the original SD1 instructpix2pix model and the
diffusers SDXL one.
8 months ago
96b4c757cf
Add log to debug custom nodes that hang when imported.
8 months ago
94a5a67c32
Cleanup to support different types of inpaint models.
8 months ago
9bf6061dfc
Switch prints to logging in folder_paths and add some extra debug.
8 months ago
5d8898c056
Fix some performance issues with weight loading and unloading.
...
Lower peak memory usage when changing model.
Fix case where model weights would be unloaded and reloaded.
8 months ago
327ca1313d
Support SDXS 0.9
8 months ago
8ae1e4d125
Make step on sharpen node smaller.
8 months ago
2f93b91646
Add Tesla GPUs to cuda malloc blacklist.
8 months ago
c9673926fb
Fix test.
8 months ago
11838e60f4
Increase the max resolution.
8 months ago
ae77590b4e
dora_scale support for lora file.
8 months ago
c6de09b02e
Optimize memory unload strategy for more optimized performance.
8 months ago
6a32c06f06
Move cleanup_models to improve performance.
8 months ago
a28a9dc836
Add an example to use the SaveImageWebsocket node and enable it.
8 months ago
0624838237
Add inverse noise scaling function.
8 months ago
5d875d77fe
Fix regression with lcm not working with batches.
8 months ago
4b9005e949
Fix regression with model merging.
8 months ago
c18a203a8a
Don't unload model weights for non weight patches.
8 months ago
150a3e946f
Make LCM sampler use the model noise scaling function.
8 months ago
d14bdb1896
Revert, NOTE: this will be removed again soon please fix your nodes.
8 months ago
0c55f16c9e
Remove code that should be useless now.
8 months ago
40e124c6be
SV3D support.
8 months ago
0b78213bda
Fix neg scale step.
8 months ago
b1a16d4500
Fix stable cascade img2img not working with all resolutions.
8 months ago
cacb022c4a
Make saved SD1 checkpoints match more closely the official one.
8 months ago
d3406d8d58
Increase image batch nodes maximum values.
8 months ago
d7897fff2c
Move cascade scale factor from stage_a to latent_formats.py
8 months ago
f2fe635c9f
SamplerDPMAdaptative node to test the different options.
8 months ago
448d9263a2
Fix control loras breaking.
8 months ago
db8b59ecff
Lower memory usage for loras in lowvram mode at the cost of perf.
8 months ago
eda8704386
Add SamplerDPMPP_3M_SDE node.
8 months ago
e7b8e240f7
Add SamplerLMS node.
8 months ago
2a813c3b09
Switch some more prints to logging.
8 months ago
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
8 months ago
dc6d4151a2
Not needed anymore.
8 months ago
03f4cfb7cd
Replace more prints with logging.
8 months ago
65397ce601
Replace prints with logging and add --verbose argument.
8 months ago
4656273e72
Added additional nodes for CLIP merging
8 months ago
comfyanonymous
MoonRide303