diff options
| author | Zac Liu <liuguang@baai.ac.cn> | 2022-12-06 01:17:57 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-12-06 01:17:57 +0000 |
| commit | a25dfebeed5b3411f2dc0f558c2b87a7c1cda420 (patch) | |
| tree | 77f08a174aba15584282670ab3714ab88a76612c /v2-inference.yaml | |
| parent | 3ebf977a6e4f478ab918e44506974beee32da276 (diff) | |
| parent | 4929503258d80abbc4b5f40da034298fe3803906 (diff) | |
| download | stable-diffusion-webui-gfx803-a25dfebeed5b3411f2dc0f558c2b87a7c1cda420.tar.gz stable-diffusion-webui-gfx803-a25dfebeed5b3411f2dc0f558c2b87a7c1cda420.tar.bz2 stable-diffusion-webui-gfx803-a25dfebeed5b3411f2dc0f558c2b87a7c1cda420.zip | |
Merge pull request #3 from 920232796/master
fix device support for mps
update the support for SD2.0
Diffstat (limited to 'v2-inference.yaml')
| -rw-r--r-- | v2-inference.yaml | 67 |
1 files changed, 67 insertions, 0 deletions
diff --git a/v2-inference.yaml b/v2-inference.yaml new file mode 100644 index 00000000..0eb25395 --- /dev/null +++ b/v2-inference.yaml @@ -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"
\ No newline at end of file |