diff --git a/audio_encoders/put_audio_encoder_models_here b/audio_encoders/put_audio_encoder_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/background_removal/put_background_removal_models_here b/background_removal/put_background_removal_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/checkpoints/scail2/sam3.1_multiplex_fp16.safetensors b/checkpoints/scail2/sam3.1_multiplex_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32845e0cc923fa2564a715d4b0aa1c8b0d447287 --- /dev/null +++ b/checkpoints/scail2/sam3.1_multiplex_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba99c92703c2e8b4f47de2d34a539bb8e18923049e238b780d70dbe6368eb03 +size 1745546848 diff --git a/clip/scail2/umt5_xxl_fp8_e4m3fn_scaled.safetensors b/clip/scail2/umt5_xxl_fp8_e4m3fn_scaled.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f67b8b88cdc897fa83f59bbd36ad54612a534ade --- /dev/null +++ b/clip/scail2/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/clip_vision/scail2/clip_vision_h.safetensors b/clip_vision/scail2/clip_vision_h.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0451a9fda3873d0db8725fcea14e5660e1793f83 --- /dev/null +++ b/clip_vision/scail2/clip_vision_h.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161 +size 1264219396 diff --git a/configs/anything_v3.yaml b/configs/anything_v3.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bcfe584ae73d60e2c7a6f89b3f7befbd487ea34 --- /dev/null +++ b/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/configs/v1-inference.yaml b/configs/v1-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d4effe569e897369918625f9d8be5603a0e6a0d6 --- /dev/null +++ b/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/configs/v1-inference_clip_skip_2.yaml b/configs/v1-inference_clip_skip_2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bcfe584ae73d60e2c7a6f89b3f7befbd487ea34 --- /dev/null +++ b/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/configs/v1-inference_clip_skip_2_fp16.yaml b/configs/v1-inference_clip_skip_2_fp16.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7eca31c7b5e571c2b1348e94ed9d69978ebd2d52 --- /dev/null +++ b/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/configs/v1-inference_fp16.yaml b/configs/v1-inference_fp16.yaml new file mode 100644 index 0000000000000000000000000000000000000000..147f42b17b835cc839338156f99e8f971df5c1aa --- /dev/null +++ b/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/configs/v1-inpainting-inference.yaml b/configs/v1-inpainting-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..45f3f82d461cd8c6109f26ec3b1da75366eda0b0 --- /dev/null +++ b/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/configs/v2-inference-v.yaml b/configs/v2-inference-v.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8ec8dfbfefe94ae8522c93017668fea78d580acf --- /dev/null +++ b/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/configs/v2-inference-v_fp32.yaml b/configs/v2-inference-v_fp32.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d5c9b9cb29ca162ade44a7c922f59e75d7d57813 --- /dev/null +++ b/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/configs/v2-inference.yaml b/configs/v2-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..152c4f3c2b36c3b246a9cb10eb8166134b0d2e1c --- /dev/null +++ b/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/configs/v2-inference_fp32.yaml b/configs/v2-inference_fp32.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0d03231f3f2c2e8ef8fbe0d781e5f3d65409ef3a --- /dev/null +++ b/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/configs/v2-inpainting-inference.yaml b/configs/v2-inpainting-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..32a9471d71b828c51bcbbabfe34c5f6c8282c803 --- /dev/null +++ b/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/controlnet/put_controlnets_and_t2i_here b/controlnet/put_controlnets_and_t2i_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/detection/put_detection_models_here b/detection/put_detection_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/diffusers/put_diffusers_models_here b/diffusers/put_diffusers_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/diffusion_models/put_diffusion_model_files_here b/diffusion_models/put_diffusion_model_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/embeddings/put_embeddings_or_textual_inversion_concepts_here b/embeddings/put_embeddings_or_textual_inversion_concepts_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/frame_interpolation/film_net_fp16.safetensors b/frame_interpolation/film_net_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a37d7ca1d473bb5c0758e00f8bd80e827c4702a --- /dev/null +++ b/frame_interpolation/film_net_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f226e51375dc839d4b40e5c3d63da560dd1ea1c962364ec78f5adf2d05db05c0 +size 68882302 diff --git a/frame_interpolation/put_frame_interpolation_models_here b/frame_interpolation/put_frame_interpolation_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/geometry_estimation/put_geometry_estimation_models_here b/geometry_estimation/put_geometry_estimation_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/gligen/put_gligen_models_here b/gligen/put_gligen_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/hypernetworks/put_hypernetworks_here b/hypernetworks/put_hypernetworks_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/latent_upscale_models/put_latent_upscale_models_here b/latent_upscale_models/put_latent_upscale_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/loras/scail2/genitals_helper_v1.0_e219.safetensors b/loras/scail2/genitals_helper_v1.0_e219.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..edac2aa42a776b1aef48b317a46a71ba63387e20 --- /dev/null +++ b/loras/scail2/genitals_helper_v1.0_e219.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379c267ca9e6021bde9763c74a76117335181b189edbcd06e29acf1d16f6af10 +size 306807976 diff --git a/loras/scail2/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors b/loras/scail2/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..591542d4e35f8ffcdec54994d513859f21699773 --- /dev/null +++ b/loras/scail2/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c4a61c30e0497aa44b91d93a893b624708461a56fe5485183b28fa07e2dfb3 +size 738005744 diff --git a/loras/scail2/wan2.1-i2v-480p-rsacp.safetensors b/loras/scail2/wan2.1-i2v-480p-rsacp.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2be5fe76d2305e414fe2675250183294f0e00ee6 --- /dev/null +++ b/loras/scail2/wan2.1-i2v-480p-rsacp.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6687ec412ba440886f393fc21ac7bd7d28797b5c6d74e1ab594b2833df0c890 +size 359257680 diff --git a/loras/scail2/wan2.1_SCAIL_2_DPO_lora_bf16.safetensors b/loras/scail2/wan2.1_SCAIL_2_DPO_lora_bf16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29f1e5e66323718e88008d83c8906ff6b89406b3 --- /dev/null +++ b/loras/scail2/wan2.1_SCAIL_2_DPO_lora_bf16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b106522036f64e50f5f8ae3b808973515ff442cc2fac27b65d875eafb95b89e2 +size 1226936552 diff --git a/loras/wanloras/170_Wan-Jiggle-Tits-HIGH-14B_feb19.safetensors b/loras/wanloras/170_Wan-Jiggle-Tits-HIGH-14B_feb19.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..199fc87d39dcd65c36b68017575fd7679d9e6057 --- /dev/null +++ b/loras/wanloras/170_Wan-Jiggle-Tits-HIGH-14B_feb19.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92cb4cce736243d92243e74cb2929e112cec3c74d0e40c132e768f75179b38be +size 306815234 diff --git a/loras/wanloras/CameraTiltDown_HIGH.safetensors b/loras/wanloras/CameraTiltDown_HIGH.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..124d57332171092993eed34ca5e3d7f58539edcb --- /dev/null +++ b/loras/wanloras/CameraTiltDown_HIGH.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb1110531f2e8d3474bd4ac6a73fe8e6aa472cd289beeb296b310f8ca5cbf9b +size 306807976 diff --git a/loras/wanloras/DR34ML4Y_I2V_14B_HIGH_V2.safetensors b/loras/wanloras/DR34ML4Y_I2V_14B_HIGH_V2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5055f094efac1e9d0be97c3f94032ddb1873229e --- /dev/null +++ b/loras/wanloras/DR34ML4Y_I2V_14B_HIGH_V2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9931756c202bd8d4946c0d163c1269231a6352b51bb4235f6a19894c9ad8c68 +size 306807976 diff --git a/loras/wanloras/DR34ML4Y_I2V_14B_LOW_V2.safetensors b/loras/wanloras/DR34ML4Y_I2V_14B_LOW_V2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92d410ed4c7570c7f031daa003927660be7cd43e --- /dev/null +++ b/loras/wanloras/DR34ML4Y_I2V_14B_LOW_V2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066ee4bfafb685c85f08174c8283cd11bc6d36f4845347f20d633ab44581601f +size 306807976 diff --git a/loras/wanloras/LowAngle_HIGH.safetensors b/loras/wanloras/LowAngle_HIGH.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4eb30a6c2fee25e0ffc66b541624b6d83c02f8b0 --- /dev/null +++ b/loras/wanloras/LowAngle_HIGH.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca8d7555793574a7101266206ddbc9090cd4776c23e620320dbbe44a61dd44e +size 153453624 diff --git a/loras/wanloras/NSFW-22-H-e8.safetensors b/loras/wanloras/NSFW-22-H-e8.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1e51801a0aa624380e22521e732d0f8ca8dce5f --- /dev/null +++ b/loras/wanloras/NSFW-22-H-e8.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e2144d3cd65360f97d09ccbe03e1c39a096df6c9234af5fe3899d1b63cda39 +size 613516752 diff --git a/loras/wanloras/NSFW-22-L-e8.safetensors b/loras/wanloras/NSFW-22-L-e8.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9aeee78e070b8a9206127c7fcd5778e6479fcbf --- /dev/null +++ b/loras/wanloras/NSFW-22-L-e8.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b783742f4d5fd63a0223ae1d5bf64fc995a6b408480ac2a00528ae0d4146db +size 613516752 diff --git a/loras/wanloras/W22_NSFW_Posing_Nude_i2v_HN_v2.safetensors b/loras/wanloras/W22_NSFW_Posing_Nude_i2v_HN_v2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cf512ceafc0d5a84ea2165fa35a1481fcd79ace --- /dev/null +++ b/loras/wanloras/W22_NSFW_Posing_Nude_i2v_HN_v2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da32a0d5b2bf68be68406059ae6f9d4542643dc94000f89d9a02a37fb025759 +size 306850360 diff --git a/loras/wanloras/W22_NSFW_Posing_Nude_i2v_LN_v2.safetensors b/loras/wanloras/W22_NSFW_Posing_Nude_i2v_LN_v2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa51b46e57ec39242fcc2882bdcf5a360f09a28b --- /dev/null +++ b/loras/wanloras/W22_NSFW_Posing_Nude_i2v_LN_v2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f0deb6c24ba640a2187749ce5c76d7772a24d755345fb622cf61d061fee70e +size 306850720 diff --git a/loras/wanloras/Wan2.2_dp_v2_HighNoise-000020.safetensors b/loras/wanloras/Wan2.2_dp_v2_HighNoise-000020.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3dbefebbf86225245aeb8e7556ec1a7e385d798 --- /dev/null +++ b/loras/wanloras/Wan2.2_dp_v2_HighNoise-000020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1fc1ee4cfdebd37764230382cc936934b4f7d34bf69586b32d23f364e5ed9f3 +size 306847576 diff --git a/loras/wanloras/Wan2.2_dp_v2_LowNoise-000018.safetensors b/loras/wanloras/Wan2.2_dp_v2_LowNoise-000018.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e7efe63ecd2cdc2f489d6df074d52e2982b7cbc --- /dev/null +++ b/loras/wanloras/Wan2.2_dp_v2_LowNoise-000018.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3a642609bb4e00a515ed7ec51bfda3c644fae0018ea45825257abeceeee460f +size 306847576 diff --git a/loras/wanloras/depantsing_spanking_high.safetensors b/loras/wanloras/depantsing_spanking_high.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1fa8483f7ffe08c320c1a2ce455dcec538f4debd --- /dev/null +++ b/loras/wanloras/depantsing_spanking_high.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d66357a65dbc08db7fb5981611dcaa0e3d6c08430206521f20d28e6d72fc7229 +size 557109840 diff --git a/loras/wanloras/depantsing_spanking_low.safetensors b/loras/wanloras/depantsing_spanking_low.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b46684934755974168aa26d273b984c17170d25f --- /dev/null +++ b/loras/wanloras/depantsing_spanking_low.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5015d7fc1f433e6c3a7c330063a65dfa63b5519481b5298ee7b671dd645912 +size 306851496 diff --git a/loras/wanloras/hard_cut_3_wan_i2v_high.safetensors b/loras/wanloras/hard_cut_3_wan_i2v_high.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6580775c5472d5aada6fb032c74773ddbb5e4ea3 --- /dev/null +++ b/loras/wanloras/hard_cut_3_wan_i2v_high.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492bf5a9cb9e770f8a2a716faf80a57c45bd53bd8cd61219a87d4d7b53378de2 +size 306807976 diff --git a/loras/wanloras/mql_cowgirl_b_v1_high_noise.safetensors b/loras/wanloras/mql_cowgirl_b_v1_high_noise.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce2ad431e69fd81ff7b3968456ae175c3a9e30f9 --- /dev/null +++ b/loras/wanloras/mql_cowgirl_b_v1_high_noise.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b64ec123ecc95cd1125774e78f9ebb2ce1735ad4f1629a3aebf2daa5ff557a6 +size 306808360 diff --git a/loras/wanloras/mql_cowgirl_b_v1_low_noise.safetensors b/loras/wanloras/mql_cowgirl_b_v1_low_noise.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8586ca5162148e6a4d179cc031106b3ce6cf26c0 --- /dev/null +++ b/loras/wanloras/mql_cowgirl_b_v1_low_noise.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a7510e8b9024f3ed99ec2ddf59c19332bb2be693e8eac9e66ba46562f860b5 +size 306808360 diff --git a/loras/wanloras/mql_dp_a_v1_high_noise.safetensors b/loras/wanloras/mql_dp_a_v1_high_noise.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d114203ba4df62220a540076a90b16019572f56b --- /dev/null +++ b/loras/wanloras/mql_dp_a_v1_high_noise.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208a93fbb3c2ea7f4474a171024e46ed611254a02c508aa7f3a2abd6bab789ed +size 306808360 diff --git a/loras/wanloras/wan2.2_i2v_high_ulitmate_pussy_asshole.safetensors b/loras/wanloras/wan2.2_i2v_high_ulitmate_pussy_asshole.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c28ed327b25682520b8a914e4519dd4c8e75d1dc --- /dev/null +++ b/loras/wanloras/wan2.2_i2v_high_ulitmate_pussy_asshole.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fb3c045b5c30a4648bca5883767edffa1b145e46d96ed70f7d07aefc01d722d +size 383524872 diff --git a/loras/wanloras/wan2.2_i2v_low_ulitmate_pussy_asshole.safetensors b/loras/wanloras/wan2.2_i2v_low_ulitmate_pussy_asshole.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..647cde8144665d11c531304f13ae95ffa9d1c1f5 --- /dev/null +++ b/loras/wanloras/wan2.2_i2v_low_ulitmate_pussy_asshole.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576a5c10bccd467d58a5e28f7c156cef1d467922b1f9296fed522c2d69df1547 +size 383524872 diff --git a/loras/wanloras/wan22-m4crom4sti4-10epoc-low-k3nk.safetensors b/loras/wanloras/wan22-m4crom4sti4-10epoc-low-k3nk.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f59b38b7ef75c34c2f9e6a455c407401ecaabc50 --- /dev/null +++ b/loras/wanloras/wan22-m4crom4sti4-10epoc-low-k3nk.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5c6b550839fffe43aa216d13a2e9ad7e362bf10733532c598bd1e5daeb9a3a +size 306807976 diff --git a/loras/wanloras/wan22-m4crom4sti4-12epoc-high-k3nk.safetensors b/loras/wanloras/wan22-m4crom4sti4-12epoc-high-k3nk.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32992fdc44f367ee1255407e52b4de7124a00054 --- /dev/null +++ b/loras/wanloras/wan22-m4crom4sti4-12epoc-high-k3nk.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee63d26eab46795dd99e9b0792e21151fd6223c986c8c75dc9cf2779aa871de +size 153453160 diff --git a/model_patches/put_model_patches_here b/model_patches/put_model_patches_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/optical_flow/put_optical_flow_models_here b/optical_flow/put_optical_flow_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/photomaker/put_photomaker_models_here b/photomaker/put_photomaker_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/style_models/put_t2i_style_model_here b/style_models/put_t2i_style_model_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/text_encoders/put_text_encoder_files_here b/text_encoders/put_text_encoder_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/unet/put_unet_files_here b/unet/put_unet_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/unet/scail2/wan2.1_14B_SCAIL_2_fp8_scaled.safetensors b/unet/scail2/wan2.1_14B_SCAIL_2_fp8_scaled.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8372ca582fed8bbf7fe00905006745d301f37ebe --- /dev/null +++ b/unet/scail2/wan2.1_14B_SCAIL_2_fp8_scaled.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11513b4697ecf566de0cb74660c478f301fb6699a62b10369e91a6ed0fd6b083 +size 17694586857 diff --git a/upscale_models/RealESRGAN_x2.pth b/upscale_models/RealESRGAN_x2.pth new file mode 100644 index 0000000000000000000000000000000000000000..313b87ab9359a04b0f450695b1a01a88edd4ac95 --- /dev/null +++ b/upscale_models/RealESRGAN_x2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c830d067d54fc767b9543a8432f36d91bc2de313584e8bbfe4ac26a47339e899 +size 67061725 diff --git a/upscale_models/put_esrgan_and_other_upscale_models_here b/upscale_models/put_esrgan_and_other_upscale_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/vae/put_vae_here b/vae/put_vae_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/vae/wan_2.1_vae.safetensors b/vae/wan_2.1_vae.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ff32b52dac309662138ca42604696d34eaad7b8 --- /dev/null +++ b/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/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here b/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391