diff options
| author | brkirch <brkirch@users.noreply.github.com> | 2023-01-04 05:40:16 +0000 |
|---|---|---|
| committer | brkirch <brkirch@users.noreply.github.com> | 2023-01-06 05:14:20 +0000 |
| commit | f6ab5a39d762a7791573d1c52ae5a3024b10e8ed (patch) | |
| tree | c3958d77a6dae42457b571dbe0f1efec7ce45dd2 /configs | |
| parent | d782a95967c9eea753df3333cd1954b6ec73eba0 (diff) | |
| parent | 3e22e294135ed0327ce9d9738655ff03c53df3c0 (diff) | |
| download | stable-diffusion-webui-gfx803-f6ab5a39d762a7791573d1c52ae5a3024b10e8ed.tar.gz stable-diffusion-webui-gfx803-f6ab5a39d762a7791573d1c52ae5a3024b10e8ed.tar.bz2 stable-diffusion-webui-gfx803-f6ab5a39d762a7791573d1c52ae5a3024b10e8ed.zip | |
Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_opt
Diffstat (limited to 'configs')
| -rw-r--r-- | configs/alt-diffusion-inference.yaml | 72 | ||||
| -rw-r--r-- | configs/v1-inference.yaml | 70 |
2 files changed, 142 insertions, 0 deletions
diff --git a/configs/alt-diffusion-inference.yaml b/configs/alt-diffusion-inference.yaml new file mode 100644 index 00000000..cfbee72d --- /dev/null +++ b/configs/alt-diffusion-inference.yaml @@ -0,0 +1,72 @@ +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: modules.xlmr.BertSeriesModelWithTransformation + params: + name: "XLMR-Large"
\ No newline at end of file diff --git a/configs/v1-inference.yaml b/configs/v1-inference.yaml new file mode 100644 index 00000000..d4effe56 --- /dev/null +++ b/configs/v1-inference.yaml @@ -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 |