diff --git a/models/checkpoints/put_checkpoints_here b/models/checkpoints/put_checkpoints_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/clip/put_clip_or_text_encoder_models_here b/models/clip/put_clip_or_text_encoder_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/clip_vision/put_clip_vision_models_here b/models/clip_vision/put_clip_vision_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/configs/anything_v3.yaml b/models/configs/anything_v3.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bcfe584ae73d60e2c7a6f89b3f7befbd487ea34 --- /dev/null +++ b/models/configs/anything_v3.yaml @@ -0,0 +1,73 @@ +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 + params: + layer: "hidden" + layer_idx: -2 diff --git a/models/configs/v1-inference.yaml b/models/configs/v1-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d4effe569e897369918625f9d8be5603a0e6a0d6 --- /dev/null +++ b/models/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 diff --git a/models/configs/v1-inference_clip_skip_2.yaml b/models/configs/v1-inference_clip_skip_2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bcfe584ae73d60e2c7a6f89b3f7befbd487ea34 --- /dev/null +++ b/models/configs/v1-inference_clip_skip_2.yaml @@ -0,0 +1,73 @@ +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 + params: + layer: "hidden" + layer_idx: -2 diff --git a/models/configs/v1-inference_clip_skip_2_fp16.yaml b/models/configs/v1-inference_clip_skip_2_fp16.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7eca31c7b5e571c2b1348e94ed9d69978ebd2d52 --- /dev/null +++ b/models/configs/v1-inference_clip_skip_2_fp16.yaml @@ -0,0 +1,74 @@ +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: + 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_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 + params: + layer: "hidden" + layer_idx: -2 diff --git a/models/configs/v1-inference_fp16.yaml b/models/configs/v1-inference_fp16.yaml new file mode 100644 index 0000000000000000000000000000000000000000..147f42b17b835cc839338156f99e8f971df5c1aa --- /dev/null +++ b/models/configs/v1-inference_fp16.yaml @@ -0,0 +1,71 @@ +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: + 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_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 diff --git a/models/configs/v1-inpainting-inference.yaml b/models/configs/v1-inpainting-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..45f3f82d461cd8c6109f26ec3b1da75366eda0b0 --- /dev/null +++ b/models/configs/v1-inpainting-inference.yaml @@ -0,0 +1,71 @@ +model: + base_learning_rate: 7.5e-05 + target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion + 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: hybrid # important + monitor: val/loss_simple_ema + scale_factor: 0.18215 + finetune_keys: null + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch + 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: 9 # 4 data + 4 downscaled image + 1 mask + 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 + diff --git a/models/configs/v2-inference-v.yaml b/models/configs/v2-inference-v.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8ec8dfbfefe94ae8522c93017668fea78d580acf --- /dev/null +++ b/models/configs/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" diff --git a/models/configs/v2-inference-v_fp32.yaml b/models/configs/v2-inference-v_fp32.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d5c9b9cb29ca162ade44a7c922f59e75d7d57813 --- /dev/null +++ b/models/configs/v2-inference-v_fp32.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: False + 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" diff --git a/models/configs/v2-inference.yaml b/models/configs/v2-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..152c4f3c2b36c3b246a9cb10eb8166134b0d2e1c --- /dev/null +++ b/models/configs/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" diff --git a/models/configs/v2-inference_fp32.yaml b/models/configs/v2-inference_fp32.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0d03231f3f2c2e8ef8fbe0d781e5f3d65409ef3a --- /dev/null +++ b/models/configs/v2-inference_fp32.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: False + 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" diff --git a/models/configs/v2-inpainting-inference.yaml b/models/configs/v2-inpainting-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..32a9471d71b828c51bcbbabfe34c5f6c8282c803 --- /dev/null +++ b/models/configs/v2-inpainting-inference.yaml @@ -0,0 +1,158 @@ +model: + base_learning_rate: 5.0e-05 + target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion + 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: hybrid + scale_factor: 0.18215 + monitor: val/loss_simple_ema + finetune_keys: null + use_ema: False + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_checkpoint: True + image_size: 32 # unused + in_channels: 9 + 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" + + +data: + target: ldm.data.laion.WebDataModuleFromConfig + params: + tar_base: null # for concat as in LAION-A + p_unsafe_threshold: 0.1 + filter_word_list: "data/filters.yaml" + max_pwatermark: 0.45 + batch_size: 8 + num_workers: 6 + multinode: True + min_size: 512 + train: + shards: + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -" #{00000-94333}.tar" + shuffle: 10000 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 512 + interpolation: 3 + - target: torchvision.transforms.RandomCrop + params: + size: 512 + postprocess: + target: ldm.data.laion.AddMask + params: + mode: "512train-large" + p_drop: 0.25 + # NOTE use enough shards to avoid empty validation loops in workers + validation: + shards: + - "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - " + shuffle: 0 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 512 + interpolation: 3 + - target: torchvision.transforms.CenterCrop + params: + size: 512 + postprocess: + target: ldm.data.laion.AddMask + params: + mode: "512train-large" + p_drop: 0.25 + +lightning: + find_unused_parameters: True + modelcheckpoint: + params: + every_n_train_steps: 5000 + + callbacks: + metrics_over_trainsteps_checkpoint: + params: + every_n_train_steps: 10000 + + image_logger: + target: main.ImageLogger + params: + enable_autocast: False + disabled: False + batch_frequency: 1000 + max_images: 4 + increase_log_steps: False + log_first_step: False + log_images_kwargs: + use_ema_scope: False + inpaint: False + plot_progressive_rows: False + plot_diffusion_rows: False + N: 4 + unconditional_guidance_scale: 5.0 + unconditional_guidance_label: [""] + ddim_steps: 50 # todo check these out for depth2img, + ddim_eta: 0.0 # todo check these out for depth2img, + + trainer: + benchmark: True + val_check_interval: 5000000 + num_sanity_val_steps: 0 + accumulate_grad_batches: 1 diff --git a/models/controlnet/put_controlnets_and_t2i_here b/models/controlnet/put_controlnets_and_t2i_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/diffusers/put_diffusers_models_here b/models/diffusers/put_diffusers_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/diffusion_models/Wan2.1/wan2.1_i2v_480p_14B_bf16.safetensors b/models/diffusion_models/Wan2.1/wan2.1_i2v_480p_14B_bf16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fa8cde628c33340d29ccbed47f68e04b7ff62eb --- /dev/null +++ b/models/diffusion_models/Wan2.1/wan2.1_i2v_480p_14B_bf16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9 +size 32789894024 diff --git a/models/diffusion_models/Wan2.1/wan2.1_i2v_480p_14B_fp8_scaled.safetensors b/models/diffusion_models/Wan2.1/wan2.1_i2v_480p_14B_fp8_scaled.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..073e9db43301a33e2c54fca00ecd16cba709e256 --- /dev/null +++ b/models/diffusion_models/Wan2.1/wan2.1_i2v_480p_14B_fp8_scaled.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395 +size 16401356938 diff --git a/models/diffusion_models/Wan2.1/wan2.1_t2v_14B_bf16.safetensors b/models/diffusion_models/Wan2.1/wan2.1_t2v_14B_bf16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00e75b0537cf61515563c670a45b6378fcad46c5 --- /dev/null +++ b/models/diffusion_models/Wan2.1/wan2.1_t2v_14B_bf16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8 +size 28577096680 diff --git a/models/diffusion_models/Wan2.1/wan2.1_t2v_14B_fp8_e4m3fn.safetensors b/models/diffusion_models/Wan2.1/wan2.1_t2v_14B_fp8_e4m3fn.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1618e8515682ef46e0dd30ebbbc3175d2a183ee --- /dev/null +++ b/models/diffusion_models/Wan2.1/wan2.1_t2v_14B_fp8_e4m3fn.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb +size 14289605920 diff --git a/models/diffusion_models/put_diffusion_model_files_here b/models/diffusion_models/put_diffusion_model_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/embeddings/put_embeddings_or_textual_inversion_concepts_here b/models/embeddings/put_embeddings_or_textual_inversion_concepts_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/gligen/put_gligen_models_here b/models/gligen/put_gligen_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/hypernetworks/put_hypernetworks_here b/models/hypernetworks/put_hypernetworks_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/loras/.gitattributes b/models/loras/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..a6344aac8c09253b3b630fb776ae94478aa0275b --- /dev/null +++ b/models/loras/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/models/loras/I2V_dildo-ride.safetensors b/models/loras/I2V_dildo-ride.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..091c9b70816a8539ba332dbce87dfc99fb985a85 --- /dev/null +++ b/models/loras/I2V_dildo-ride.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9190f3528f5369587742a26c7f9ee97f0375e460ae7f9d6d7b47b5a879a7127d +size 306807976 diff --git a/models/loras/I2V_h4ndp4nties_v2_14B.safetensors b/models/loras/I2V_h4ndp4nties_v2_14B.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..182e66a275ab63b2939f39d3c986b2e3638e78a5 --- /dev/null +++ b/models/loras/I2V_h4ndp4nties_v2_14B.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531e612b27f92550cf462153873e02bf391d6fd19d456959a3884c7cbb7e2340 +size 359257680 diff --git a/models/loras/Jenna_Ortega_T2V.safetensors b/models/loras/Jenna_Ortega_T2V.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68f1cc357b8282e338023f8281968f023bdecea3 --- /dev/null +++ b/models/loras/Jenna_Ortega_T2V.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9468144c18ae1e705a9f03b067edd25c58c2be2f2ceb3cfaed174b2e681b25bd +size 306807976 diff --git a/models/loras/MagicWan_converted.safetensors b/models/loras/MagicWan_converted.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08363bbde9ca1bdb3a3fe55ef926d21ebdb0248a --- /dev/null +++ b/models/loras/MagicWan_converted.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59248a829d4dfa1f04ace09e4521221de632d677ad3c0347464dd2ce34261705 +size 153454992 diff --git a/models/loras/P001-SideSex-Wan-i2v-v10-000010_converted.safetensors b/models/loras/P001-SideSex-Wan-i2v-v10-000010_converted.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da315feb4f73bc5a401f2724e7f69b8e02d994d4 --- /dev/null +++ b/models/loras/P001-SideSex-Wan-i2v-v10-000010_converted.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8c93c88d810a2cb98be1725f5dc5afdd1b2420806d71cc3887053ef649355e +size 359259456 diff --git a/models/loras/T22V_wan_wtsstadamit.safetensors b/models/loras/T22V_wan_wtsstadamit.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe27b5b58753f32b34efae5bd736046f26f0529b --- /dev/null +++ b/models/loras/T22V_wan_wtsstadamit.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b1e11827b6dfee86f0962818e592d2129fae79420c4167e0b26c8a7a1861aba +size 306807976 diff --git a/models/loras/T2V-I2V_h4nd_p4nties_v3.safetensors b/models/loras/T2V-I2V_h4nd_p4nties_v3.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9279a814308fee67f8b7108b961b60634f96a556 --- /dev/null +++ b/models/loras/T2V-I2V_h4nd_p4nties_v3.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f11ad720cae3b8f6d95d48c1ac79c7f2e1de16b39414c0a1d6cdbfad741d8e +size 306807976 diff --git a/models/loras/T2V_fetish_rebel.safetensors b/models/loras/T2V_fetish_rebel.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..523ace9da9ff5babe250888050b65747db27ffc7 --- /dev/null +++ b/models/loras/T2V_fetish_rebel.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323128355a84f870247c7e0f06f3b1e4758c5a39a9eab14faadac8b5995057d9 +size 306807976 diff --git a/models/loras/WAN_Passionate_Kissing_v1.safetensors b/models/loras/WAN_Passionate_Kissing_v1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ff0e4231faf4e7971ba4c1ea82349d8a4a21cb2 --- /dev/null +++ b/models/loras/WAN_Passionate_Kissing_v1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846f4b91468772ba8e6ef2bb5e5be1294bd88f04a753436e1ef1de380bc926ce +size 153453160 diff --git a/models/loras/Wan-Doggy-14b-I2V-v1.safetensors b/models/loras/Wan-Doggy-14b-I2V-v1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d33f0afd85f945083a6ad40e015c56ca5c2e2e41 --- /dev/null +++ b/models/loras/Wan-Doggy-14b-I2V-v1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fab3191f3854f4be084e537f98afc09098a488f6469d7edbd5f7c825dd0b817 +size 359261096 diff --git a/models/loras/Wan-Doggy_v2-t2v_i2v.safetensors b/models/loras/Wan-Doggy_v2-t2v_i2v.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f302479557a0f4997b9c87d11e20f85e71d23fec --- /dev/null +++ b/models/loras/Wan-Doggy_v2-t2v_i2v.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d64766843407d3f774c29c44f94bd35642c6e41a2ff1d64d595f150644cbfda4 +size 306812376 diff --git a/models/loras/boob_grab_epoch045.safetensors b/models/loras/boob_grab_epoch045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85073a6edac8a416265e10f374a4ce76477401d4 --- /dev/null +++ b/models/loras/boob_grab_epoch045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad843bee0043065dc0f7f3ebfb264561599ad5e0c126a3b9ca1a2b7c3801ca0 +size 306807976 diff --git a/models/loras/detailz-wan.safetensors b/models/loras/detailz-wan.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b70cbb95768c170ccc7e0491fb18a29e2fecfc3 --- /dev/null +++ b/models/loras/detailz-wan.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e87dccd1ce65ceba4ab9590bf59bb5fe1a73edc8eba622a413862eaa8818f87 +size 306807616 diff --git a/models/loras/dildo_ride-14b-v2.safetensors b/models/loras/dildo_ride-14b-v2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7a7b2f60ccfb7b780fab417013f38252ee252d6 --- /dev/null +++ b/models/loras/dildo_ride-14b-v2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc54c82ebcbf1f1faa1773d99b504252ee08ab1806a2571ca3828790693631ab +size 306807976 diff --git a/models/loras/doggy_diffusers.safetensors b/models/loras/doggy_diffusers.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1418d2678e257c9158c7b88419c097d802144da2 --- /dev/null +++ b/models/loras/doggy_diffusers.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959dc85aa56b270430d11b08c19e302833793ce2d33074a141a3bd49ffd082e4 +size 306809720 diff --git a/models/loras/doggy_pov_9fingers.safetensors b/models/loras/doggy_pov_9fingers.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f976d59dd890c58dd6494fe176d147f21fe9ad36 --- /dev/null +++ b/models/loras/doggy_pov_9fingers.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f0f8205fb6b6236a5953d009f9f009c72f72b0c77a8ee8c89ece0fbeb17354 +size 306809920 diff --git a/models/loras/emma_watson-T2V.safetensors b/models/loras/emma_watson-T2V.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8227c2c2c2b28a73121b7bba7ab8629c185888f --- /dev/null +++ b/models/loras/emma_watson-T2V.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72df1e7af699533583d276818aa3568ebcd9820b190d56e3cbfd4628dc40b8da +size 306807976 diff --git a/models/loras/front_doggy_plow_v1e60.safetensors b/models/loras/front_doggy_plow_v1e60.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a27523fea4f9c4afd670bcfb03018cb7c614371 --- /dev/null +++ b/models/loras/front_doggy_plow_v1e60.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c216b5a112dab5efb74cab7f24bd70a14d52908bea11a96577920e74dbe92aa +size 538826520 diff --git a/models/loras/jenna_coleman-T2V.safetensors b/models/loras/jenna_coleman-T2V.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..418e910293ebf56e68325ffa45b1d0d27cb790e6 --- /dev/null +++ b/models/loras/jenna_coleman-T2V.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f13775708f7e1590c51eacea9011855b8866ee190d7dbba74c3e2fdbfad62ea +size 306807976 diff --git a/models/loras/l3z_kiss.safetensors b/models/loras/l3z_kiss.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a238d09814718f77e96ceed8b6ef68046185e12 --- /dev/null +++ b/models/loras/l3z_kiss.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7399e3e535c0f8413feebf85037eb7f10fc384dc31b569020f26d7084ef30026 +size 306807976 diff --git a/models/loras/ntm.safetensors b/models/loras/ntm.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4fd984a4729c8f6dbb0a2df7fe939e10f30a4d6 --- /dev/null +++ b/models/loras/ntm.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda304a6eaf36f0433d84dd3b3614b1a63a5af81bb6f77c9de0c3775b1f301f7 +size 350068192 diff --git a/models/loras/photoshooting.safetensors b/models/loras/photoshooting.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d80ac1ce3dfe838406eab9c339b7d84c6b2f1c4 --- /dev/null +++ b/models/loras/photoshooting.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b4b6c03c4a2ae2d93772050234d62b3b27b1169e33a842ec07b8b22da29997 +size 306807640 diff --git a/models/loras/pov_anal_wan14b_insert_epoch090.safetensors b/models/loras/pov_anal_wan14b_insert_epoch090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dda95502caab9efe93b35b759a5bb00aa7858e71 --- /dev/null +++ b/models/loras/pov_anal_wan14b_insert_epoch090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2617ee65440d0eacae0e3ffccfff1b42a38ccbfc4105e119e7a06544eaf4665 +size 306807976 diff --git a/models/loras/sexmachine-shura-000003.safetensors b/models/loras/sexmachine-shura-000003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a3468957fdccff302140aff4f2df19eb1494631 --- /dev/null +++ b/models/loras/sexmachine-shura-000003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2846e433ee2f48024fb5134d478e6cbcb706986ef2d20294f085c554a0e4849b +size 359306608 diff --git a/models/loras/str1p_v1.safetensors b/models/loras/str1p_v1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55deecb597fde719ff78c1bf828bdef4f5cb0fbe --- /dev/null +++ b/models/loras/str1p_v1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9deedf78630532df8fc2fdda98020c39354a93ea4f5cfffdfdb92d600e914114 +size 306807976 diff --git a/models/loras/str1p_v2.safetensors b/models/loras/str1p_v2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ea639202ba41c33e166de7ace58b374d3663f94 --- /dev/null +++ b/models/loras/str1p_v2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4658ee20e820a7f11282616e844c4826acd17c7aa172c513f32b4f8db06e2556 +size 322519480 diff --git a/models/loras/wan-nsfw-e14-fixed.safetensors b/models/loras/wan-nsfw-e14-fixed.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06d205964bb712eda8bfb2e6ad6a3e5376cf6ae9 --- /dev/null +++ b/models/loras/wan-nsfw-e14-fixed.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9795720988c72cae6b0a9c262de5fdcb606add8799b6e23444fd889e505a0d11 +size 613516752 diff --git a/models/loras/wan_cowgirl_v1.1.safetensors b/models/loras/wan_cowgirl_v1.1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b665b1935a2e3800fc24d12109e2dc7aa3b8919 --- /dev/null +++ b/models/loras/wan_cowgirl_v1.1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b834fe48bd31848b8d3b287c70054b11364ca75663ee483ead5e9ccc8be5f8b +size 306807976 diff --git a/models/loras/wan_cowgirl_v1.2.safetensors b/models/loras/wan_cowgirl_v1.2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b104508dc1adc4c3ae70c8ced541e748061637b2 --- /dev/null +++ b/models/loras/wan_cowgirl_v1.2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a57e0d81b595cdd9100dc6eb31e64fbb0041c4c892f17a2d8318a83cb58dc3e +size 306807976 diff --git a/models/loras/wan_double_blowjob.safetensors b/models/loras/wan_double_blowjob.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dca48d302456ec2078018e166fb857a7a20ab997 --- /dev/null +++ b/models/loras/wan_double_blowjob.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87f80b0cc6946b11f872f762c7a604a3f21ee287c3b9bf5a75427604293f024 +size 306807976 diff --git a/models/loras/wan_female_masturbation.safetensors b/models/loras/wan_female_masturbation.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d2504cd04098cd6ff0a37bc022488990373d527 --- /dev/null +++ b/models/loras/wan_female_masturbation.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abe4560de57cdfbf131d9c3884cf3e83648948aeb41c4a073edd2e571652eea +size 306807976 diff --git a/models/loras/wan_missionary_side.safetensors b/models/loras/wan_missionary_side.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85e0298cd47b026787eab89de0fea8d5e95ed205 --- /dev/null +++ b/models/loras/wan_missionary_side.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9269b1ad928e8b8dd24931e3d4567015eb16b843162118c950eace2c1eeea8 +size 306807976 diff --git a/models/loras/wan_pov_blowjob.safetensors b/models/loras/wan_pov_blowjob.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6bfbabb818d9f62b90886474221b4babcdf6e04 --- /dev/null +++ b/models/loras/wan_pov_blowjob.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54b85fca8aa3c1c97fce3c44ff2b65a6c53aa192bfb182f61134733d556e89b +size 306807976 diff --git a/models/loras/wan_pov_missionary.safetensors b/models/loras/wan_pov_missionary.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2b188b1b7e14fca995790586a21125048d88cef --- /dev/null +++ b/models/loras/wan_pov_missionary.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7812bb4a43043a20baf51018ea625adc51e8fbc654296e735fa2af486c6b5b6f +size 306807976 diff --git a/models/loras/wan_pov_missionary_v1.1.safetensors b/models/loras/wan_pov_missionary_v1.1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..228fc736bca882932e250e6d680c9b1009b8a53e --- /dev/null +++ b/models/loras/wan_pov_missionary_v1.1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23fbe8eedcfd69b3ca4b68986dff9a937316cd32c9e606aaccb3d56ea18f7536 +size 306807976 diff --git a/models/loras/wan_tittydrop_v1_t2v_1.3b.safetensors b/models/loras/wan_tittydrop_v1_t2v_1.3b.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a7df7f10bee25705d9943f89d5c180aeb83117c --- /dev/null +++ b/models/loras/wan_tittydrop_v1_t2v_1.3b.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9a634778756375165490df05ba46d605e2432f34e34f1b61b2cb969e80a43f +size 87564160 diff --git a/models/loras/wan_tittydrop_v1_t2v_14b.safetensors b/models/loras/wan_tittydrop_v1_t2v_14b.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d841f70984d42248aaf7e15260b2b62c550f18e7 --- /dev/null +++ b/models/loras/wan_tittydrop_v1_t2v_14b.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a74b8092f8b193fcd3d6a20aee78296b15bdfe549c6dd7e017a9562a5b5442 +size 306807976 diff --git a/models/loras/woman_undressing_v1.0_wan14b_epoch048.safetensors b/models/loras/woman_undressing_v1.0_wan14b_epoch048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d1684e46d946a7f5bd93d971777fe20dd9fcafe --- /dev/null +++ b/models/loras/woman_undressing_v1.0_wan14b_epoch048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db457606ced4521f7c91132e2fd0f7ed1e3dd94451aa19109b5baf966ee242e +size 306807976 diff --git a/models/photomaker/put_photomaker_models_here b/models/photomaker/put_photomaker_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/sams/sam_vit_b_01ec64.pth b/models/sams/sam_vit_b_01ec64.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab7d111e57bd052a76fe669986560e3555e9c8f6 --- /dev/null +++ b/models/sams/sam_vit_b_01ec64.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2df62732614e57411cdcf32a23ffdf28910380d03139ee0f4fcbe91eb8c912 +size 375042383 diff --git a/models/style_models/put_t2i_style_model_here b/models/style_models/put_t2i_style_model_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/text_encoders/clip_vision_h.safetensors b/models/text_encoders/clip_vision_h.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0451a9fda3873d0db8725fcea14e5660e1793f83 --- /dev/null +++ b/models/text_encoders/clip_vision_h.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161 +size 1264219396 diff --git a/models/text_encoders/open-clip-xlm-roberta-large-vit-huge-14_visual_fp16.safetensors b/models/text_encoders/open-clip-xlm-roberta-large-vit-huge-14_visual_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3c754eafa72f1f9c9170679fa2119691d6665041 --- /dev/null +++ b/models/text_encoders/open-clip-xlm-roberta-large-vit-huge-14_visual_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d8d80a37826639eeecd9d7cb972a8b387215c3d26e4f0b8e415a1c97b343da +size 1264195610 diff --git a/models/text_encoders/open-clip-xlm-roberta-large-vit-huge-14_visual_fp32.safetensors b/models/text_encoders/open-clip-xlm-roberta-large-vit-huge-14_visual_fp32.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9d1eed77e1af21d8636e8584c49dd831cbec8cf --- /dev/null +++ b/models/text_encoders/open-clip-xlm-roberta-large-vit-huge-14_visual_fp32.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f086b055939277030025242998f0a55a500d20ad67e38e11032b2a6f6d6ef7 +size 2528349548 diff --git a/models/text_encoders/put_text_encoder_files_here b/models/text_encoders/put_text_encoder_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/text_encoders/umt5_xxl_fp16.safetensors b/models/text_encoders/umt5_xxl_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9aa640a3a4ba42fcb2baa7c929a0e0ec9cdc9968 --- /dev/null +++ b/models/text_encoders/umt5_xxl_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af +size 11366399385 diff --git a/models/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors b/models/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f67b8b88cdc897fa83f59bbd36ad54612a534ade --- /dev/null +++ b/models/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68 +size 6735906897 diff --git a/models/unet/put_unet_files_here b/models/unet/put_unet_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/upscale_models/4xLSDIR.pth b/models/upscale_models/4xLSDIR.pth new file mode 100644 index 0000000000000000000000000000000000000000..258f79657af41fbad91fc3cfd773ee6674eb804e --- /dev/null +++ b/models/upscale_models/4xLSDIR.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a743089e6395091b0073c15b4392c3c658ee32841ba770c15c27d92426e5901 +size 67020037 diff --git a/models/upscale_models/put_esrgan_and_other_upscale_models_here b/models/upscale_models/put_esrgan_and_other_upscale_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/vae/put_vae_here b/models/vae/put_vae_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/vae/taew2_1.safetensors b/models/vae/taew2_1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..324e639c077783440d794ce95f5a40b0fc13152e --- /dev/null +++ b/models/vae/taew2_1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a870ebc6a8bc36bb4124c304341e7b258ab4010e365743fbac2dc43af98cf9b2 +size 22642926 diff --git a/models/vae/wan_2.1_vae.safetensors b/models/vae/wan_2.1_vae.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ff32b52dac309662138ca42604696d34eaad7b8 --- /dev/null +++ b/models/vae/wan_2.1_vae.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b +size 253815318 diff --git a/models/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here b/models/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391