1580158
/
stable-diffusion-aws-extension
mirror of https://github.com/awslabs/stable-diffusion-aws-extension.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

mkdir ControlNet

pull/683/head
Jingyi 2024-04-17 10:45:06 +08:00
parent 6321596c1e
commit cf10bf1a23
34 changed files with 969 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test/.gitignore vendored
View File

@ -27,3 +27,5 @@ tmp.png
response.json
schema.json
oas.json
.ckpt
s5cmd

1
test/config.py
View File

@ -49,7 +49,6 @@ logger.info(f"config.is_local: {is_local}")
role_name = "role_name"
logger.info(f"config.role_name: {role_name}")
current_time = datetime.utcnow().strftime("%m-%d-%H-%M-%S")
endpoint_name = f"test-{current_time}"

0
test/data/comfy/checkpoints/put_checkpoints_here Normal file
View File

0
test/data/comfy/clip/put_clip_or_text_encoder_models_here Normal file
View File

0
test/data/comfy/clip_vision/put_clip_vision_models_here Normal file
View File

73
test/data/comfy/configs/anything_v3.yaml Normal file
View File

@ -0,0 +1,73 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
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: 4
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
params:
layer: "hidden"
layer_idx: -2

70
test/data/comfy/configs/v1-inference.yaml Normal file
View File

@ -0,0 +1,70 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
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: 4
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

73
test/data/comfy/configs/v1-inference_clip_skip_2.yaml Normal file
View File

@ -0,0 +1,73 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
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: 4
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
params:
layer: "hidden"
layer_idx: -2

74
test/data/comfy/configs/v1-inference_clip_skip_2_fp16.yaml Normal file
View File

@ -0,0 +1,74 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
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_fp16: True
image_size: 32 # unused
in_channels: 4
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
params:
layer: "hidden"
layer_idx: -2

71
test/data/comfy/configs/v1-inference_fp16.yaml Normal file
View File

@ -0,0 +1,71 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
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_fp16: True
image_size: 32 # unused
in_channels: 4
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

71
test/data/comfy/configs/v1-inpainting-inference.yaml Normal file
View File

@ -0,0 +1,71 @@
model:
base_learning_rate: 7.5e-05
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
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
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:
image_size: 32 # unused
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_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

68
test/data/comfy/configs/v2-inference-v.yaml Normal file
View File

@ -0,0 +1,68 @@
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
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
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
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.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"

68
test/data/comfy/configs/v2-inference-v_fp32.yaml Normal file
View File

@ -0,0 +1,68 @@
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: False
image_size: 32 # unused
in_channels: 4
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
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
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.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"

67
test/data/comfy/configs/v2-inference.yaml Normal file
View File

@ -0,0 +1,67 @@
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: True
image_size: 32 # unused
in_channels: 4
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
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
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.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"

67
test/data/comfy/configs/v2-inference_fp32.yaml Normal file
View File

@ -0,0 +1,67 @@
model:
base_learning_rate: 1.0e-4
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False # we set this to false because this is an inference only config
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
use_fp16: False
image_size: 32 # unused
in_channels: 4
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
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
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.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"

158
test/data/comfy/configs/v2-inpainting-inference.yaml Normal file
View File

@ -0,0 +1,158 @@
model:
base_learning_rate: 5.0e-05
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: hybrid
scale_factor: 0.18215
monitor: val/loss_simple_ema
finetune_keys: null
use_ema: False
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
use_checkpoint: True
image_size: 32 # unused
in_channels: 9
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
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
#attn_type: "vanilla-xformers"
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.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
data:
target: ldm.data.laion.WebDataModuleFromConfig
params:
tar_base: null # for concat as in LAION-A
p_unsafe_threshold: 0.1
filter_word_list: "data/filters.yaml"
max_pwatermark: 0.45
batch_size: 8
num_workers: 6
multinode: True
min_size: 512
train:
shards:
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -" #{00000-94333}.tar"
shuffle: 10000
image_key: jpg
image_transforms:
- target: torchvision.transforms.Resize
params:
size: 512
interpolation: 3
- target: torchvision.transforms.RandomCrop
params:
size: 512
postprocess:
target: ldm.data.laion.AddMask
params:
mode: "512train-large"
p_drop: 0.25
# NOTE use enough shards to avoid empty validation loops in workers
validation:
shards:
- "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
shuffle: 0
image_key: jpg
image_transforms:
- target: torchvision.transforms.Resize
params:
size: 512
interpolation: 3
- target: torchvision.transforms.CenterCrop
params:
size: 512
postprocess:
target: ldm.data.laion.AddMask
params:
mode: "512train-large"
p_drop: 0.25
lightning:
find_unused_parameters: True
modelcheckpoint:
params:
every_n_train_steps: 5000
callbacks:
metrics_over_trainsteps_checkpoint:
params:
every_n_train_steps: 10000
image_logger:
target: main.ImageLogger
params:
enable_autocast: False
disabled: False
batch_frequency: 1000
max_images: 4
increase_log_steps: False
log_first_step: False
log_images_kwargs:
use_ema_scope: False
inpaint: False
plot_progressive_rows: False
plot_diffusion_rows: False
N: 4
unconditional_guidance_scale: 5.0
unconditional_guidance_label: [""]
ddim_steps: 50 # todo check these out for depth2img,
ddim_eta: 0.0 # todo check these out for depth2img,
trainer:
benchmark: True
val_check_interval: 5000000
num_sanity_val_steps: 0
accumulate_grad_batches: 1

0
test/data/comfy/controlnet/put_controlnets_and_t2i_here Normal file
View File

0
test/data/comfy/diffusers/put_diffusers_models_here Normal file
View File

0
test/data/comfy/embeddings/put_embeddings_or_textual_inversion_concepts_here Normal file
View File

0
test/data/comfy/gligen/put_gligen_models_here Normal file
View File

0
test/data/comfy/hypernetworks/put_hypernetworks_here Normal file
View File

0
test/data/comfy/loras/put_loras_here Normal file
View File

0
test/data/comfy/photomaker/put_photomaker_models_here Normal file
View File

0
test/data/comfy/style_models/put_t2i_style_model_here Normal file
View File

0
test/data/comfy/unet/put_unet_files_here Normal file
View File

0
test/data/comfy/upscale_models/put_esrgan_and_other_upscale_models_here Normal file
View File

0
test/data/comfy/vae/put_vae_here Normal file
View File

0
test/data/comfy/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here Normal file
View File

48
test/test_06_api_inference/test_05_comfy_sync_files.py Normal file
View File

@ -0,0 +1,48 @@
from __future__ import print_function
import logging
import os
import uuid
import config as config
from utils.api import Api
from utils.helper import wget_file
logger = logging.getLogger(__name__)
endpoint_name = f"comfy-async-{config.endpoint_name}"
id = str(uuid.uuid4())
class TestComfySyncFiles:
def setup_class(self):
self.api = Api(config)
@classmethod
def teardown_class(self):
pass
def test_0_download_file(self):
local_path = f"./data/comfy/checkpoints/v1-5-pruned-emaonly.ckpt"
wget_file(
local_path,
'https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt'
)
def test_1_sync_files_to_comfy_endpoint(self):
local = "'./data/comfy/*'"
target = f"'s3://{config.bucket}/comfy/{endpoint_name}/{id}/models/'"
logger.info(f"Syncing {local} to {target}")
os.system(f"rm -rf ./s5cmd")
os.system(f"wget -q ./ https://raw.githubusercontent.com/elonniu/s5cmd/main/s5cmd")
os.system(f"chmod +x ./s5cmd")
os.system(f"./s5cmd sync {local} {target}")
def test_2_sync_files(self):
data = {"endpoint_name": f"{endpoint_name}",
"need_reboot": True,
"prepare_id": id,
"prepare_type": "models"}
self.api.prepare(data=data)

0
test/test_06_api_inference/test_05_comfy_create_and_get.py → test/test_06_api_inference/test_06_comfy_create_and_get.py
View File

0
test/test_06_api_inference/test_06_comfy_query_and_delete.py → test/test_06_api_inference/test_07_comfy_query_and_delete.py
View File

3
test/test_06_api_inference/test_41_sd_xl_turbo.py
View File

@ -177,7 +177,8 @@ class TestTurboE2E:
if status == InferenceStatus.FAILED.value:
logger.error(resp.dumps())
logger.error(inference_data)
raise Exception(f"Inference job {inference_id} failed.")
break
# raise Exception(f"Inference job {inference_id} failed.")
time.sleep(5)
else:
raise Exception("Inference timed out after 4 minutes.")

48
test/test_08_api_inference_re/test_00_comfy_sync_files.py Normal file
View File

@ -0,0 +1,48 @@
from __future__ import print_function
import logging
import os
import uuid
import config as config
from utils.api import Api
from utils.helper import wget_file
logger = logging.getLogger(__name__)
endpoint_name = f"comfy-async-{config.endpoint_name}"
id = str(uuid.uuid4())
class TestComfyReSyncFiles:
def setup_class(self):
self.api = Api(config)
@classmethod
def teardown_class(self):
pass
def test_0_download_file(self):
local_path = f"./data/comfy/checkpoints/v1-5-pruned-emaonly.ckpt"
wget_file(
local_path,
'https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt'
)
def test_1_sync_files_to_comfy_endpoint(self):
local = "'./data/comfy/*'"
target = f"'s3://{config.bucket}/comfy/{endpoint_name}/{id}/models/'"
logger.info(f"Syncing {local} to {target}")
os.system(f"rm -rf ./s5cmd")
os.system(f"wget -q ./ https://raw.githubusercontent.com/elonniu/s5cmd/main/s5cmd")
os.system(f"chmod +x ./s5cmd")
os.system(f"./s5cmd sync {local} {target}")
def test_2_sync_files(self):
data = {"endpoint_name": f"{endpoint_name}",
"need_reboot": True,
"prepare_id": id,
"prepare_type": "models"}
self.api.prepare(data=data)

9
test/utils/api.py
View File

@ -164,6 +164,15 @@ class Api:
params=params
)
def prepare(self, headers=None, data=None):
return self.req(
"POST",
"prepare",
headers=headers,
operation_id='',
data=data
)
def create_role(self, headers=None, data=None):
return self.req(
"POST",