InvokeAI/invokeai/configs/stable-diffusion/v2-inference.yaml
Lincoln Stein 2f9dcd7906 support both epsilon and v-prediction v2 inference
There are actually two Stable Diffusion v2 legacy checkpoint
configurations:

1) "epsilon" prediction type for Stable Diffusion v2 Base
2) "v-prediction" type for Stable Diffusion v2-768

This commit adds the configuration file needed for epsilon prediction
type models as well as the UI that prompts the user to select the
appropriate configuration file when the code can't do so
automatically.
2023-03-05 22:51:40 -05:00

68 lines
1.8 KiB
YAML

model:
base_learning_rate: 1.0e-4
target: invokeai.backend.stable_diffusion.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: invokeai.backend.stable_diffusion.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: invokeai.backend.stable_diffusion.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: invokeai.backend.stable_diffusion.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"