parser.add_argument(
        "--aesthetic_lr",
        type=int,
        help="learning rate for the aesthetic personalization",
        default=0.00001,
    )

    parser.add_argument(
        "--aesthetic_lr",
        type=float,
        help="learning rate for the aesthetic personalization",
        default=0.00001,
    )

 python scripts/txt2img.py --prompt "Roman city on top of a ridge, sci-fi illustration by Greg Rutkowski #sci-fi detailed vivid colors gothic concept illustration by James Gurney and Zdzislaw Beksiński vivid vivid colorsg concept illustration colorful interior" --seed 332 --plms  --aesthetic_steps 2 --W 768 --aesthetic_embedding aesthetic_embeddings/laion_7plus.pt --n_samples 1 --ckpt v1-5-pruned-emaonly.ckpt 
Global seed set to 332
Loading model from v1-5-pruned-emaonly.ckpt
Global Step: 840000
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Some weights of the model checkpoint at openai/clip-vit-large-patch14 were not used when initializing CLIPTextModel: ['vision_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.bias', 'vision_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.encoder.layers.22.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.layer_norm1.bias', 'vision_model.encoder.layers.16.layer_norm2.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.weight', 'vision_model.post_layernorm.bias', 'vision_model.encoder.layers.19.layer_norm2.weight', 'vision_model.encoder.layers.14.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.encoder.layers.17.mlp.fc2.bias', 'vision_model.encoder.layers.19.layer_norm2.bias', 'vision_model.encoder.layers.15.layer_norm1.bias', 'vision_model.encoder.layers.20.layer_norm1.weight', 'vision_model.encoder.layers.15.mlp.fc1.bias', 'vision_model.encoder.layers.13.mlp.fc2.bias', 'vision_model.encoder.layers.9.layer_norm1.bias', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.layer_norm2.weight', 'vision_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.encoder.layers.21.layer_norm1.weight', 'vision_model.encoder.layers.14.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.self_attn.out_proj.weight', 'vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.encoder.layers.20.layer_norm2.bias', 'vision_model.encoder.layers.15.layer_norm1.weight', 'vision_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.encoder.layers.14.self_attn.k_proj.bias', 'vision_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.layer_norm1.weight', 'vision_model.encoder.layers.9.layer_norm2.bias', 'vision_model.embeddings.position_ids', 'vision_model.encoder.layers.1.mlp.fc1.weight', 'text_projection.weight', 'vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.mlp.fc1.bias', 'vision_model.encoder.layers.23.mlp.fc1.bias', 'vision_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.encoder.layers.14.mlp.fc2.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.encoder.layers.16.layer_norm2.bias', 'vision_model.embeddings.class_embedding', 'vision_model.encoder.layers.18.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.layer_norm2.bias', 'vision_model.encoder.layers.22.self_attn.k_proj.bias', 'vision_model.encoder.layers.17.layer_norm2.weight', 'vision_model.encoder.layers.19.self_attn.k_proj.weight', 'vision_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.encoder.layers.12.layer_norm1.weight', 'vision_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.encoder.layers.11.layer_norm2.weight', 'vision_model.encoder.layers.10.layer_norm2.weight', 'vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.encoder.layers.12.mlp.fc2.bias', 'vision_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.encoder.layers.13.self_attn.v_proj.weight', 'vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.layer_norm1.bias', 'vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.encoder.layers.2.layer_norm1.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.bias', 'vision_model.encoder.layers.20.self_attn.q_proj.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.weight', 'vision_model.encoder.layers.22.self_attn.k_proj.weight', 'vision_model.encoder.layers.7.layer_norm2.weight', 'vision_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.mlp.fc2.bias', 'vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.encoder.layers.23.self_attn.v_proj.bias', 'vision_model.post_layernorm.weight', 'vision_model.encoder.layers.16.mlp.fc1.weight', 'vision_model.encoder.layers.19.self_attn.q_proj.bias', 'visual_projection.weight', 'vision_model.encoder.layers.20.mlp.fc2.weight', 'vision_model.encoder.layers.14.self_attn.k_proj.weight', 'vision_model.encoder.layers.12.self_attn.out_proj.weight', 'vision_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.layer_norm1.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.bias', 'vision_model.encoder.layers.16.layer_norm1.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.mlp.fc2.bias', 'vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.encoder.layers.18.layer_norm1.weight', 'vision_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.encoder.layers.9.layer_norm1.weight', 'vision_model.encoder.layers.18.mlp.fc2.bias', 'vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.encoder.layers.17.mlp.fc1.bias', 'vision_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.encoder.layers.16.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.mlp.fc1.bias', 'vision_model.encoder.layers.13.layer_norm1.weight', 'vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.mlp.fc2.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.encoder.layers.22.mlp.fc1.weight', 'vision_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.layer_norm2.bias', 'vision_model.encoder.layers.16.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.encoder.layers.16.self_attn.out_proj.bias', 'vision_model.encoder.layers.15.self_attn.v_proj.bias', 'vision_model.encoder.layers.14.layer_norm2.bias', 'vision_model.encoder.layers.15.layer_norm2.weight', 'vision_model.encoder.layers.23.self_attn.k_proj.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.layer_norm1.bias', 'vision_model.encoder.layers.13.mlp.fc1.bias', 'vision_model.encoder.layers.22.self_attn.out_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.bias', 'vision_model.encoder.layers.16.self_attn.out_proj.weight', 'vision_model.encoder.layers.13.self_attn.v_proj.bias', 'vision_model.encoder.layers.21.mlp.fc1.weight', 'vision_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.embeddings.position_embedding.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.encoder.layers.13.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.encoder.layers.23.layer_norm2.bias', 'vision_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.encoder.layers.21.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.weight', 'vision_model.encoder.layers.23.layer_norm1.weight', 'vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.encoder.layers.19.mlp.fc2.weight', 'vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.encoder.layers.4.layer_norm2.weight', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.encoder.layers.19.mlp.fc1.weight', 'vision_model.encoder.layers.17.mlp.fc1.weight', 'vision_model.encoder.layers.4.layer_norm1.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.encoder.layers.21.mlp.fc2.weight', 'vision_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.encoder.layers.8.layer_norm2.bias', 'vision_model.encoder.layers.16.self_attn.q_proj.weight', 'vision_model.encoder.layers.23.self_attn.out_proj.bias', 'vision_model.encoder.layers.14.mlp.fc1.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.bias', 'vision_model.encoder.layers.17.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.layer_norm1.weight', 'vision_model.encoder.layers.17.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.mlp.fc1.bias', 'vision_model.encoder.layers.14.layer_norm1.bias', 'vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.encoder.layers.18.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.encoder.layers.16.layer_norm1.bias', 'vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.layer_norm1.weight', 'vision_model.encoder.layers.21.mlp.fc2.bias', 'vision_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.self_attn.v_proj.weight', 'vision_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.encoder.layers.12.layer_norm2.weight', 'vision_model.encoder.layers.4.layer_norm2.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.weight', 'vision_model.encoder.layers.22.layer_norm2.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.bias', 'vision_model.encoder.layers.22.mlp.fc1.bias', 'vision_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.encoder.layers.18.mlp.fc2.weight', 'vision_model.encoder.layers.18.mlp.fc1.bias', 'vision_model.encoder.layers.21.self_attn.out_proj.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.weight', 'vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.encoder.layers.17.layer_norm1.weight', 'vision_model.encoder.layers.21.layer_norm2.bias', 'vision_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.encoder.layers.2.layer_norm2.bias', 'vision_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.encoder.layers.22.layer_norm2.bias', 'vision_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.encoder.layers.17.layer_norm2.bias', 'vision_model.encoder.layers.13.self_attn.k_proj.bias', 'vision_model.encoder.layers.20.self_attn.out_proj.bias', 'vision_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.encoder.layers.14.layer_norm1.weight', 'vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.pre_layrnorm.weight', 'vision_model.encoder.layers.21.self_attn.q_proj.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.weight', 'vision_model.encoder.layers.3.layer_norm1.bias', 'vision_model.encoder.layers.12.mlp.fc1.bias', 'vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.encoder.layers.13.layer_norm1.bias', 'vision_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.layer_norm2.weight', 'vision_model.encoder.layers.20.mlp.fc2.bias', 'vision_model.encoder.layers.11.layer_norm1.weight', 'vision_model.encoder.layers.12.self_attn.v_proj.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.layer_norm2.weight', 'vision_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.encoder.layers.2.self_attn.q_proj.bias', 'vision_model.encoder.layers.16.self_attn.v_proj.bias', 'vision_model.encoder.layers.15.layer_norm2.bias', 'vision_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.encoder.layers.19.layer_norm1.weight', 'vision_model.encoder.layers.6.layer_norm1.weight', 'vision_model.encoder.layers.13.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.bias', 'vision_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.weight', 'vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.weight', 'vision_model.encoder.layers.17.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.layer_norm2.bias', 'vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.encoder.layers.13.layer_norm2.weight', 'vision_model.encoder.layers.14.layer_norm2.weight', 'vision_model.encoder.layers.23.self_attn.k_proj.bias', 'vision_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.weight', 'vision_model.encoder.layers.21.self_attn.q_proj.weight', 'vision_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.mlp.fc1.weight', 'vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.encoder.layers.3.layer_norm1.weight', 'vision_model.encoder.layers.12.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.encoder.layers.10.layer_norm1.bias', 'vision_model.encoder.layers.6.self_attn.out_proj.weight', 'vision_model.encoder.layers.23.layer_norm2.weight', 'vision_model.encoder.layers.20.self_attn.q_proj.bias', 'vision_model.encoder.layers.20.mlp.fc1.weight', 'vision_model.encoder.layers.11.layer_norm1.bias', 'vision_model.encoder.layers.17.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.encoder.layers.23.mlp.fc2.bias', 'vision_model.encoder.layers.14.mlp.fc2.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.encoder.layers.13.mlp.fc1.weight', 'vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.encoder.layers.7.layer_norm2.bias', 'vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.encoder.layers.21.self_attn.out_proj.bias', 'logit_scale', 'vision_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.encoder.layers.13.mlp.fc2.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.mlp.fc2.weight', 'vision_model.encoder.layers.17.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.self_attn.q_proj.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.bias', 'vision_model.encoder.layers.12.layer_norm1.bias', 'vision_model.encoder.layers.23.mlp.fc1.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.encoder.layers.12.self_attn.q_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.layer_norm2.weight', 'vision_model.encoder.layers.12.self_attn.out_proj.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.bias', 'vision_model.encoder.layers.18.layer_norm1.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.encoder.layers.10.layer_norm2.bias', 'vision_model.encoder.layers.1.layer_norm2.bias', 'vision_model.encoder.layers.1.layer_norm2.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.self_attn.q_proj.bias', 'vision_model.encoder.layers.23.layer_norm1.bias', 'vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.encoder.layers.20.self_attn.v_proj.bias', 'vision_model.encoder.layers.3.layer_norm2.bias', 'vision_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.encoder.layers.3.layer_norm2.weight', 'vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.encoder.layers.10.layer_norm1.weight', 'vision_model.encoder.layers.23.self_attn.q_proj.weight', 'vision_model.encoder.layers.19.self_attn.q_proj.weight', 'vision_model.encoder.layers.6.layer_norm1.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.bias', 'vision_model.encoder.layers.23.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.layer_norm1.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.weight', 'vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.encoder.layers.14.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.self_attn.v_proj.bias', 'vision_model.encoder.layers.17.layer_norm1.bias', 'vision_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.pre_layrnorm.bias', 'vision_model.encoder.layers.7.layer_norm1.bias', 'vision_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.encoder.layers.20.self_attn.k_proj.bias', 'vision_model.encoder.layers.14.mlp.fc1.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.bias', 'vision_model.encoder.layers.18.layer_norm2.weight', 'vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.encoder.layers.21.self_attn.v_proj.bias', 'vision_model.encoder.layers.23.self_attn.v_proj.weight', 'vision_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.encoder.layers.18.mlp.fc1.weight', 'vision_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.self_attn.q_proj.bias', 'vision_model.encoder.layers.18.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.bias', 'vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.encoder.layers.9.layer_norm2.weight', 'vision_model.encoder.layers.19.layer_norm1.bias', 'vision_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.encoder.layers.22.mlp.fc2.bias', 'vision_model.encoder.layers.20.mlp.fc1.bias', 'vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.q_proj.bias', 'vision_model.encoder.layers.17.self_attn.k_proj.weight', 'vision_model.encoder.layers.4.layer_norm1.weight', 'vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.encoder.layers.23.mlp.fc2.weight', 'vision_model.encoder.layers.17.mlp.fc2.weight', 'vision_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.encoder.layers.2.layer_norm1.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.layer_norm1.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.encoder.layers.23.self_attn.q_proj.bias', 'vision_model.encoder.layers.20.layer_norm2.weight', 'vision_model.encoder.layers.12.mlp.fc2.weight', 'vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.encoder.layers.5.layer_norm2.weight', 'vision_model.encoder.layers.11.layer_norm2.bias', 'vision_model.encoder.layers.12.mlp.fc1.weight', 'vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.encoder.layers.11.mlp.fc1.weight']
- This IS expected if you are initializing CLIPTextModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing CLIPTextModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Creating invisible watermark encoder (see https://github.com/ShieldMnt/invisible-watermark)...
Sampling:   0%|                                                                          | 0/2 [00:00<?, ?it/s/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/encoders/modules.py:232: UserWarning: The use of `x.T` on tensors of dimension other than 2 to reverse their shape is deprecated and it will throw an error in a future release. Consider `x.mT` to transpose batches of matricesor `x.permute(*torch.arange(x.ndim - 1, -1, -1))` to reverse the dimensions of a tensor. (Triggered internally at  /opt/conda/conda-bld/pytorch_1656352465323/work/aten/src/ATen/native/TensorShape.cpp:2981.)
  sim = text_embs @ image_embs.T
tensor([0.1159], device='cuda:0', dtype=torch.float16, grad_fn=<NegBackward0>)
tensor([0.0503], device='cuda:0', dtype=torch.float16, grad_fn=<NegBackward0>)
tensor([-0.0100], device='cuda:0', dtype=torch.float16, grad_fn=<NegBackward0>)
Data shape for PLMS sampling is (1, 4, 64, 96)
Running PLMS Sampling with 50 timesteps
PLMS Sampler: 100%|████████████████████████████████████████████████████████████| 50/50 [00:28<00:00,  1.77it/s]
data: 100%|██████████████████████████████████████████████████████████████████████| 1/1 [00:38<00:00, 38.07s/it]
Sampling:  50%|█████████████████████████████████                                 | 1/2 [00:38<00:38, 38.07s/ittensor([0.1159], device='cuda:0', dtype=torch.float16, grad_fn=<NegBackward0>)            | 0/1 [00:00<?, ?it/s]
tensor([0.0503], device='cuda:0', dtype=torch.float16, grad_fn=<NegBackward0>)
tensor([-0.0100], device='cuda:0', dtype=torch.float16, grad_fn=<NegBackward0>)
Data shape for PLMS sampling is (1, 4, 64, 96)
Running PLMS Sampling with 50 timesteps
PLMS Sampler:   0%|                                                                     | 0/50 [00:00<?, ?it/s]
data:   0%|                                                                              | 0/1 [00:05<?, ?it/s]
Sampling:  50%|█████████████████████████████████                                 | 1/2 [00:43<00:43, 43.32s/it]
Traceback (most recent call last):
  File "scripts/txt2img.py", line 394, in <module>
    main()
  File "scripts/txt2img.py", line 331, in main
    samples_ddim, _ = sampler.sample(
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/models/diffusion/plms.py", line 97, in sample
    samples, intermediates = self.plms_sampling(conditioning, size,
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/models/diffusion/plms.py", line 152, in plms_sampling
    outs = self.p_sample_plms(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/models/diffusion/plms.py", line 218, in p_sample_plms
    e_t = get_model_output(x, t)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/models/diffusion/plms.py", line 185, in get_model_output
    e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/models/diffusion/ddpm.py", line 987, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/models/diffusion/ddpm.py", line 1410, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/diffusionmodules/openaimodel.py", line 732, in forward
    h = module(h, emb, context)
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/diffusionmodules/openaimodel.py", line 85, in forward
    x = layer(x, context)
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/attention.py", line 258, in forward
    x = block(x, context=context)
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/attention.py", line 209, in forward
    return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/diffusionmodules/util.py", line 114, in checkpoint
    return CheckpointFunction.apply(func, len(inputs), *args)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/diffusionmodules/util.py", line 127, in forward
    output_tensors = ctx.run_function(*ctx.input_tensors)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/attention.py", line 212, in _forward
    x = self.attn1(self.norm1(x)) + x
  File "/opt/conda/envs/ldm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/alegorr/repo_test/stable-diffusion-aesthetic-gradients/ldm/modules/attention.py", line 189, in forward
    attn = sim.softmax(dim=-1)
RuntimeError: CUDA out of memory. Tried to allocate 2.25 GiB (GPU 0; 14.56 GiB total capacity; 8.77 GiB already allocated; 1.50 GiB free; 12.13 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation.  See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF