22 Commits (main)

Author SHA1 Message Date
comfyanonymous 1589b58d3e Basic Flux Schnell and Flux Dev model implementation. 7 months ago
comfyanonymous 821f93872e Allow model sampling to set number of timesteps. 7 months ago
comfyanonymous 2dc84d1444 Add a way to set the timestep multiplier in the flow sampling. 8 months ago
comfyanonymous bb1969cab7 Initial support for the stable audio open model. 8 months ago
comfyanonymous 8c4a9befa7 SD3 Support. 9 months ago
comfyanonymous 0624838237 Add inverse noise scaling function. 11 months ago
comfyanonymous 478f71a249 Remove useless check. 12 months ago
comfyanonymous c62e836167 Move noise scaling to object with sampling math. 12 months ago
comfyanonymous d46583ecec Playground V2.5 support with ModelSamplingContinuousEDM node.
Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.
1 year ago
comfyanonymous c6b7a157ed Align simple scheduling closer to official stable cascade scheduler. 1 year ago
comfyanonymous 8b60d33bb7 Add ModelSamplingStableCascade to control the shift sampling parameter.
shift is 2.0 by default on Stage C and 1.0 by default on Stage B.
1 year ago
comfyanonymous 5b40e7a5ed Implement shift schedule for cascade stage C. 1 year ago
comfyanonymous f83109f09b Stable Cascade Stage C. 1 year ago
comfyanonymous c661a8b118 Don't use numpy for calculating sigmas. 1 year ago
comfyanonymous a4ec54a40d Add linear_start and linear_end to model_config.sampling_settings 1 year ago
comfyanonymous f30b992b18 .sigma and .timestep now return tensors on the same device as the input. 1 year ago
comfyanonymous 871cc20e13 Support SVD img2vid model. 1 year ago
comfyanonymous 32447f0c39 Add sampling_settings so models can specify specific sampling settings. 1 year ago
comfyanonymous d9d8702d8d percent_to_sigma now returns a float instead of a tensor. 1 year ago
comfyanonymous dcec1047e6 Invert the start and end percentages in the code.
This doesn't affect how percentages behave in the frontend but breaks
things if you relied on them in the backend.

percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion.

Make percent 0 return an extremely large sigma and percent 1.0 return a
zero one to fix imprecision.
1 year ago
comfyanonymous 844dbf97a7 Add: advanced->model->ModelSamplingDiscrete node.
This allows changing the sampling parameters of the model (eps or vpred)
or set the model to use zsnr.
1 year ago
comfyanonymous 1ffa8858e7 Move model sampling code to comfy/model_sampling.py 1 year ago