Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Refactored ControNet support to consolidate multiple parameters into data struct. Also redid how multiple controlnets are handled.

Browse Source
This commit is contained in:
user1
2023-05-12 01:43:47 -07:00
committed by Kent Keirsey
parent d15bb88eb2
commit 11fc7e40a5
2 changed files with 28 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/backend/stable_diffusion/diffusers_pipeline.py
View File

@ -670,6 +670,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
else:
latent_control_input = latent_model_input
# control_data should be type List[ControlNetData]
# this loop covers both ControlNet (one ControlNetData in list)
# and MultiControlNet (multiple ControlNetData in list)
for i, control_datum in enumerate(control_data):
@ -699,6 +700,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
for samples_prev, samples_curr in zip(down_block_res_samples, down_samples)
]
mid_block_res_sample += mid_sample
# predict the noise residual
noise_pred = self.invokeai_diffuser.do_diffusion_step(
latent_model_input,