diff options
author | AUTOMATIC1111 <16777216c@gmail.com> | 2023-01-13 11:57:38 +0000 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-01-13 11:57:38 +0000 |
commit | 9cd7716753c5be47f76b8e5555cc3e7c0f17d34d (patch) | |
tree | 345be78dd1991b77fcf4519bc44097e975e0b0c4 /v2-inference-v.yaml | |
parent | 18f86e41f6f289042c075bff1498e620ab997b8c (diff) | |
parent | 544e7a233e994f379dd67df08f5f519290b10293 (diff) | |
download | stable-diffusion-webui-gfx803-9cd7716753c5be47f76b8e5555cc3e7c0f17d34d.tar.gz stable-diffusion-webui-gfx803-9cd7716753c5be47f76b8e5555cc3e7c0f17d34d.tar.bz2 stable-diffusion-webui-gfx803-9cd7716753c5be47f76b8e5555cc3e7c0f17d34d.zip |
Merge branch 'master' into tensorboard
Diffstat (limited to 'v2-inference-v.yaml')
-rw-r--r-- | v2-inference-v.yaml | 68 |
1 files changed, 68 insertions, 0 deletions
diff --git a/v2-inference-v.yaml b/v2-inference-v.yaml new file mode 100644 index 00000000..513cd635 --- /dev/null +++ b/v2-inference-v.yaml @@ -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"
\ No newline at end of file |