Unverified Commit 56c83e45 authored by Spaceginner's avatar Spaceginner
Browse files

Merge remote-tracking branch 'origin/master'

parents 9ecf1e82 63391419

configs/instruct-pix2pix.yaml

0 → 100644
+99 −0
Original line number Diff line number Diff line 
# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).

# See more details in LICENSE.



model:

  base_learning_rate: 1.0e-04

  target: modules.models.diffusion.ddpm_edit.LatentDiffusion

  params:

    linear_start: 0.00085

    linear_end: 0.0120

    num_timesteps_cond: 1

    log_every_t: 200

    timesteps: 1000

    first_stage_key: edited

    cond_stage_key: edit

    # image_size: 64

    # image_size: 32

    image_size: 16

    channels: 4

    cond_stage_trainable: false   # Note: different from the one we trained before

    conditioning_key: hybrid

    monitor: val/loss_simple_ema

    scale_factor: 0.18215

    use_ema: true

    load_ema: true



    scheduler_config: # 10000 warmup steps

      target: ldm.lr_scheduler.LambdaLinearScheduler

      params:

        warm_up_steps: [ 0 ]

        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases

        f_start: [ 1.e-6 ]

        f_max: [ 1. ]

        f_min: [ 1. ]



    unet_config:

      target: ldm.modules.diffusionmodules.openaimodel.UNetModel

      params:

        image_size: 32 # unused

        in_channels: 8

        out_channels: 4

        model_channels: 320

        attention_resolutions: [ 4, 2, 1 ]

        num_res_blocks: 2

        channel_mult: [ 1, 2, 4, 4 ]

        num_heads: 8

        use_spatial_transformer: True

        transformer_depth: 1

        context_dim: 768

        use_checkpoint: True

        legacy: False



    first_stage_config:

      target: ldm.models.autoencoder.AutoencoderKL

      params:

        embed_dim: 4

        monitor: val/rec_loss

        ddconfig:

          double_z: true

          z_channels: 4

          resolution: 256

          in_channels: 3

          out_ch: 3

          ch: 128

          ch_mult:

          - 1

          - 2

          - 4

          - 4

          num_res_blocks: 2

          attn_resolutions: []

          dropout: 0.0

        lossconfig:

          target: torch.nn.Identity



    cond_stage_config:

      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder



data:

  target: main.DataModuleFromConfig

  params:

    batch_size: 128

    num_workers: 1

    wrap: false

    validation:

      target: edit_dataset.EditDataset

      params:

        path: data/clip-filtered-dataset

        cache_dir:  data/

        cache_name: data_10k

        split: val

        min_text_sim: 0.2

        min_image_sim: 0.75

        min_direction_sim: 0.2

        max_samples_per_prompt: 1

        min_resize_res: 512

        max_resize_res: 512

        crop_res: 512

        output_as_edit: False

        real_input: True

v2-inference-v.yaml→configs/v1-inpainting-inference.yaml

+19 −17
Original line number Diff line number Diff line 
model:

  base_learning_rate: 1.0e-4

  target: ldm.models.diffusion.ddpm.LatentDiffusion

  base_learning_rate: 7.5e-05

  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion

  params:

    parameterization: "v"

    linear_start: 0.00085

    linear_end: 0.0120

    num_timesteps_cond: 1
@@ -12,29 +11,36 @@ model: 
    cond_stage_key: "txt"

    image_size: 64

    channels: 4

    cond_stage_trainable: false

    conditioning_key: crossattn

    cond_stage_trainable: false   # Note: different from the one we trained before

    conditioning_key: hybrid   # important

    monitor: val/loss_simple_ema

    scale_factor: 0.18215

    use_ema: False # we set this to false because this is an inference only config

    finetune_keys: null



    scheduler_config: # 10000 warmup steps

      target: ldm.lr_scheduler.LambdaLinearScheduler

      params:

        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch

        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases

        f_start: [ 1.e-6 ]

        f_max: [ 1. ]

        f_min: [ 1. ]



    unet_config:

      target: ldm.modules.diffusionmodules.openaimodel.UNetModel

      params:

        use_checkpoint: True

        use_fp16: True

        image_size: 32 # unused

        in_channels: 4

        in_channels: 9  # 4 data + 4 downscaled image + 1 mask

        out_channels: 4

        model_channels: 320

        attention_resolutions: [ 4, 2, 1 ]

        num_res_blocks: 2

        channel_mult: [ 1, 2, 4, 4 ]

        num_head_channels: 64 # need to fix for flash-attn

        num_heads: 8

        use_spatial_transformer: True

        use_linear_in_transformer: True

        transformer_depth: 1

        context_dim: 1024

        context_dim: 768

        use_checkpoint: True

        legacy: False



    first_stage_config:
@@ -43,7 +49,6 @@ model: 
        embed_dim: 4

        monitor: val/rec_loss

        ddconfig:

          #attn_type: "vanilla-xformers"

          double_z: true

          z_channels: 4

          resolution: 256
@@ -62,7 +67,4 @@ model: 
          target: torch.nn.Identity



    cond_stage_config:

      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder

      params:

        freeze: True

        layer: "penultimate"
 
 No newline at end of file
 
      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

modules/api/api.py

+3 −2
Original line number Diff line number Diff line
@@ -18,7 +18,8 @@ from modules.textual_inversion.textual_inversion import create_embedding, train_ 
from modules.textual_inversion.preprocess import preprocess

from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork

from PIL import PngImagePlugin,Image

from modules.sd_models import checkpoints_list, find_checkpoint_config

from modules.sd_models import checkpoints_list

from modules.sd_models_config import find_checkpoint_config_near_filename

from modules.realesrgan_model import get_realesrgan_models

from modules import devices

from typing import List
@@ -387,7 +388,7 @@ class Api: 
        ]



    def get_sd_models(self):

        return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config(x)} for x in checkpoints_list.values()]

        return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config_near_filename(x)} for x in checkpoints_list.values()]



    def get_hypernetworks(self):

        return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks]

modules/api/models.py

+1 −1
Original line number Diff line number Diff line
@@ -228,7 +228,7 @@ class SDModelItem(BaseModel): 
    hash: Optional[str] = Field(title="Short hash")

    sha256: Optional[str] = Field(title="sha256 hash")

    filename: str = Field(title="Filename")

    config: str = Field(title="Config file")

    config: Optional[str] = Field(title="Config file")



class HypernetworkItem(BaseModel):

    name: str = Field(title="Name")

modules/devices.py

+10 −4
Original line number Diff line number Diff line
@@ -34,14 +34,18 @@ def get_cuda_device_string(): 
    return "cuda"





def get_optimal_device():

def get_optimal_device_name():

    if torch.cuda.is_available():

        return torch.device(get_cuda_device_string())

        return get_cuda_device_string()



    if has_mps():

        return torch.device("mps")

        return "mps"



    return "cpu"



    return cpu



def get_optimal_device():

    return torch.device(get_optimal_device_name())





def get_device_for(task):
@@ -139,6 +143,8 @@ def test_for_nans(x, where): 
    else:

        message = "A tensor with all NaNs was produced."



    message += " Use --disable-nan-check commandline argument to disable this check."



    raise NansException(message)

CRA Git | Maintained and supported by SUSTech CRA and CCSE