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

Merge branch 'main' into feat/nodes/add-w-h-latentsoutput

Browse Source
This commit is contained in:
blessedcoolant
2023-05-12 15:23:29 +12:00
committed by GitHub
parent 93ced0bec6 0ece4686aa
commit 0acb8ed85d
33 changed files with 301 additions and 255 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
invokeai/app/invocations/latent.py
View File

@ -17,6 +17,7 @@ from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import Post
from ...backend.image_util.seamless import configure_model_padding
from ...backend.prompting.conditioning import get_uc_and_c_and_ec
from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline, image_resized_to_grid_as_tensor
from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
import numpy as np
from ..services.image_storage import ImageType
@ -75,29 +76,20 @@ def build_noise_output(latents_name: str, latents: torch.Tensor):
)
# TODO: this seems like a hack
scheduler_map = dict(
ddim=diffusers.DDIMScheduler,
dpmpp_2=diffusers.DPMSolverMultistepScheduler,
k_dpm_2=diffusers.KDPM2DiscreteScheduler,
k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
k_euler=diffusers.EulerDiscreteScheduler,
k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
k_heun=diffusers.HeunDiscreteScheduler,
k_lms=diffusers.LMSDiscreteScheduler,
plms=diffusers.PNDMScheduler,
)
SAMPLER_NAME_VALUES = Literal[
tuple(list(scheduler_map.keys()))
tuple(list(SCHEDULER_MAP.keys()))
]
def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
scheduler_class = scheduler_map.get(scheduler_name,'ddim')
scheduler = scheduler_class.from_config(model.scheduler.config)
scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
scheduler_config = model.scheduler.config
if "_backup" in scheduler_config:
scheduler_config = scheduler_config["_backup"]
scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
scheduler = scheduler_class.from_config(scheduler_config)
# hack copied over from generate.py
if not hasattr(scheduler, 'uses_inpainting_model'):
scheduler.uses_inpainting_model = lambda: False
@ -169,7 +161,7 @@ class TextToLatentsInvocation(BaseInvocation):
noise: Optional[LatentsField] = Field(description="The noise to use")
steps: int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
scheduler: SAMPLER_NAME_VALUES = Field(default="lms", description="The scheduler to use" )
model: str = Field(default="", description="The model to use (currently ignored)")
seamless: bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
@ -237,7 +229,7 @@ class TextToLatentsInvocation(BaseInvocation):
h_symmetry_time_pct=None,#h_symmetry_time_pct,
v_symmetry_time_pct=None#v_symmetry_time_pct,
),
).add_scheduler_args_if_applicable(model.scheduler, eta=None)#ddim_eta)
).add_scheduler_args_if_applicable(model.scheduler, eta=0.0)#ddim_eta)
return conditioning_data
@ -312,11 +304,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
latent, device=model.device, dtype=latent.dtype
)
timesteps, _ = model.get_img2img_timesteps(
self.steps,
self.strength,
device=model.device,
)
timesteps, _ = model.get_img2img_timesteps(self.steps, self.strength)
result_latents, result_attention_map_saver = model.latents_from_embeddings(
latents=initial_latents,