Spaces:
Runtime error
Runtime error
| { | |
| "hashes": { | |
| "checkpoint/v1-5-pruned-emaonly.safetensors": { | |
| "mtime": 1692314737.0, | |
| "sha256": "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa" | |
| }, | |
| "checkpoint/sd_xl_base_1.0.safetensors": { | |
| "mtime": 1690358783.0, | |
| "sha256": "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b" | |
| } | |
| }, | |
| "safetensors-metadata": { | |
| "lora/sd_xl_offset_example-lora_1.0": { | |
| "mtime": 1690358783.0, | |
| "value": { | |
| "ss_adaptive_noise_scale": "None", | |
| "ss_base_model_version": "sdxl_base_v0-9", | |
| "ss_cache_latents": "True", | |
| "ss_caption_dropout_every_n_epochs": "0", | |
| "ss_caption_dropout_rate": "0.0", | |
| "ss_caption_tag_dropout_rate": "0.0", | |
| "ss_clip_skip": "None", | |
| "ss_dataset_dirs": { | |
| "": { | |
| "n_repeats": 1, | |
| "img_count": 7412 | |
| } | |
| }, | |
| "ss_datasets": "[{\"is_dreambooth\": true, \"batch_size_per_device\": 1, \"num_train_images\": 7412, \"num_reg_images\": 0, \"resolution\": [1024, 1024], \"enable_bucket\": false, \"min_bucket_reso\": null, \"max_bucket_reso\": null, \"tag_frequency\": {\"\": {\"contrast\": 7412}}, \"bucket_info\": null, \"subsets\": [{\"img_count\": 7412, \"num_repeats\": 1, \"color_aug\": false, \"flip_aug\": false, \"random_crop\": false, \"shuffle_caption\": false, \"keep_tokens\": 1, \"image_dir\": \"\", \"class_tokens\": \"contrast\", \"is_reg\": false}]}]", | |
| "ss_epoch": "4", | |
| "ss_face_crop_aug_range": "None", | |
| "ss_full_fp16": "False", | |
| "ss_gradient_accumulation_steps": "1", | |
| "ss_gradient_checkpointing": "False", | |
| "ss_learning_rate": "0.0009", | |
| "ss_lowram": "False", | |
| "ss_lr_scheduler": "cosine_with_restarts", | |
| "ss_lr_warmup_steps": "100", | |
| "ss_max_grad_norm": "1.0", | |
| "ss_max_token_length": "None", | |
| "ss_max_train_steps": "7750", | |
| "ss_min_snr_gamma": "None", | |
| "ss_mixed_precision": "fp16", | |
| "ss_multires_noise_discount": "0.3", | |
| "ss_multires_noise_iterations": "None", | |
| "ss_network_alpha": "1", | |
| "ss_network_args": { | |
| "conv_dim": "8" | |
| }, | |
| "ss_network_dim": "8", | |
| "ss_network_dropout": "None", | |
| "ss_network_module": "networks.lora", | |
| "ss_new_sd_model_hash": "a0f13b7eb4f4807f6863db3da874cb01e3cd0d5e2c481b6b01b8ea4a3139542c", | |
| "ss_noise_offset": "0.2", | |
| "ss_num_batches_per_epoch": "155", | |
| "ss_num_epochs": "50", | |
| "ss_num_reg_images": "0", | |
| "ss_num_train_images": "7412", | |
| "ss_optimizer": "transformers.optimization.Adafactor(scale_parameter=False,relative_step=False,warmup_init=False)", | |
| "ss_output_name": "offset_0.2", | |
| "ss_prior_loss_weight": "1.0", | |
| "ss_scale_weight_norms": "None", | |
| "ss_sd_model_hash": "b1facb5b", | |
| "ss_sd_model_name": "SDXL_1-0.safetensors", | |
| "ss_sd_scripts_commit_hash": "71a6d49d0663fbdeacab11c1050c33384695122b", | |
| "ss_seed": "42", | |
| "ss_session_id": "2452006521", | |
| "ss_steps": "620", | |
| "ss_tag_frequency": { | |
| "": { | |
| "contrast": 7412 | |
| } | |
| }, | |
| "ss_text_encoder_lr": "None", | |
| "ss_training_comment": "None", | |
| "ss_training_finished_at": "1689972654.070616", | |
| "ss_training_started_at": "1689970447.43792", | |
| "ss_unet_lr": "None", | |
| "ss_v2": "False", | |
| "sshs_legacy_hash": "fec84cf7", | |
| "sshs_model_hash": "8e3e833226b356a1bb9688b472e8e36315cd8a656f1a2d576bc13edd251392dd", | |
| "modelspec.sai_model_spec": "1.0.0", | |
| "modelspec.architecture": "stable-diffusion-xl-v1-base/lora", | |
| "modelspec.title": "SDXL 1.0 Official Offset Example LoRA", | |
| "modelspec.author": "StabilityAI", | |
| "modelspec.description": "This is an example LoRA for SDXL 1.0 (Base) that adds Offset Noise to the model, trained by KaliYuga for StabilityAI. When applied, it will extend the image's contrast (range of brightness to darkness), which is particularly popular for producing very dark or nighttime images. At low percentages, it improves contrast and perceived image quality; at higher percentages it can be a powerful tool to produce perfect inky black. This small file (50 megabytes) demonstrates the power of LoRA on SDXL and produces a clear visual upgrade to the base model without needing to replace the 6.5 gigabyte full model. The LoRA was heavily trained with the keyword `contrasts`, which can be used alter the high-contrast effect of offset noise.", | |
| "modelspec.usage_hint": "Recommended strength: 50% (0.5). The keyword `contrasts` may alter the effect.", | |
| "modelspec.date": "2023-07-26", | |
| "modelspec.resolution": "1024x1024", | |
| "modelspec.prediction_type": "epsilon", | |
| "modelspec.license": "CreativeML Open RAIL++-M License", | |
| "modelspec.thumbnail": "data:image/jpeg;base64,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", | |
| "modelspec.hash_sha256": "0x8e3e833226b356a1bb9688b472e8e36315cd8a656f1a2d576bc13edd251392dd" | |
| } | |
| }, | |
| "lora/szdnpp_lora_v1": { | |
| "mtime": 1692334745.0, | |
| "value": { | |
| "ss_network_dim": "128", | |
| "ss_num_epochs": "10", | |
| "ss_reg_dataset_dirs": {}, | |
| "ss_face_crop_aug_range": "None", | |
| "ss_sd_model_name": "runwayml/stable-diffusion-v1-5", | |
| "ss_max_token_length": "None", | |
| "ss_multires_noise_discount": "0.3", | |
| "ss_max_train_steps": "3200", | |
| "ss_caption_dropout_every_n_epochs": "0", | |
| "ss_seed": "420420420", | |
| "ss_learning_rate": "None", | |
| "ss_training_comment": "sszdnpp", | |
| "ss_num_train_images": "320", | |
| "ss_dataset_dirs": { | |
| "10_szdnpp woman": { | |
| "n_repeats": 10, | |
| "img_count": 32 | |
| } | |
| }, | |
| "sshs_model_hash": "f4edac6000fcbc1d33ab59c681605d77da2e0fcf656893791abcd2adc6277d53", | |
| "modelspec.implementation": "diffusers", | |
| "ss_steps": "3200", | |
| "ss_tag_frequency": { | |
| "10_szdnpp woman": { | |
| "szdnpp woman": 32 | |
| }, | |
| "4_woman": {}, | |
| "6_woman": {} | |
| }, | |
| "ss_keep_tokens": "0", | |
| "modelspec.resolution": "768x768", | |
| "ss_min_bucket_reso": "128", | |
| "ss_bucket_no_upscale": "True", | |
| "ss_color_aug": "False", | |
| "ss_cache_latents": "True", | |
| "ss_unet_lr": "None", | |
| "ss_session_id": "243271588", | |
| "modelspec.sai_model_spec": "1.0.0", | |
| "ss_network_alpha": "64.0", | |
| "ss_gradient_accumulation_steps": "1", | |
| "modelspec.title": "szdnpp_lora_v1", | |
| "ss_num_reg_images": "0", | |
| "ss_lr_warmup_steps": "0", | |
| "ss_network_dropout": "None", | |
| "ss_random_crop": "False", | |
| "ss_epoch": "10", | |
| "ss_prior_loss_weight": "1.0", | |
| "ss_text_encoder_lr": "None", | |
| "ss_lr_scheduler": "adafactor:0.0001", | |
| "sshs_legacy_hash": "d7f0f78b", | |
| "ss_full_fp16": "False", | |
| "ss_flip_aug": "False", | |
| "ss_max_bucket_reso": "2048", | |
| "ss_bucket_info": { | |
| "buckets": { | |
| "0": { | |
| "resolution": [ | |
| 512, | |
| 512 | |
| ], | |
| "count": 320 | |
| } | |
| }, | |
| "mean_img_ar_error": 0.0 | |
| }, | |
| "ss_adaptive_noise_scale": "None", | |
| "ss_max_grad_norm": "1.0", | |
| "ss_zero_terminal_snr": "False", | |
| "ss_optimizer": "transformers.optimization.Adafactor(relative_step=True)", | |
| "ss_num_batches_per_epoch": "320", | |
| "ss_sd_scripts_commit_hash": "ee37a5311d3591caffa8c7ebe798ec2bb870ed87", | |
| "ss_min_snr_gamma": "None", | |
| "ss_batch_size_per_device": "1", | |
| "ss_gradient_checkpointing": "False", | |
| "ss_network_module": "networks.lora", | |
| "modelspec.prediction_type": "epsilon", | |
| "ss_scale_weight_norms": "None", | |
| "ss_multires_noise_iterations": "None", | |
| "ss_output_name": "szdnpp_lora_v1", | |
| "ss_total_batch_size": "1", | |
| "ss_shuffle_caption": "False", | |
| "modelspec.date": "2023-08-18T04:58:07", | |
| "ss_caption_tag_dropout_rate": "0.0", | |
| "ss_clip_skip": "None", | |
| "ss_resolution": "(768, 768)", | |
| "ss_caption_dropout_rate": "0.0", | |
| "ss_v2": "False", | |
| "ss_noise_offset": "0.0", | |
| "ss_enable_bucket": "True", | |
| "ss_mixed_precision": "fp16", | |
| "ss_lowram": "False", | |
| "ss_training_started_at": "1692333214.5576196", | |
| "modelspec.architecture": "stable-diffusion-v1/lora", | |
| "ss_base_model_version": "sd_v1", | |
| "ss_training_finished_at": "1692334687.9210682" | |
| } | |
| } | |
| }, | |
| "extensions-git": { | |
| "Stable-Diffusion-Webui-Civitai-Helper": { | |
| "mtime": 1692335674.0, | |
| "value": { | |
| "remote": "https://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper.git", | |
| "commit_date": 1684842802, | |
| "branch": "main", | |
| "commit_hash": "920ca3267f789a72e3225c99f069bf0be0db795d", | |
| "version": "920ca326" | |
| } | |
| }, | |
| "Hypernetwork-MonkeyPatch-Extension": { | |
| "mtime": 1692335697.0, | |
| "value": { | |
| "remote": "https://github.com/aria1th/Hypernetwork-MonkeyPatch-Extension.git", | |
| "commit_date": 1690546730, | |
| "branch": "main", | |
| "commit_hash": "bd47167526e59c9cf3fdd8e8de364dbae96550df", | |
| "version": "bd471675" | |
| } | |
| } | |
| } | |
| } |