Delete files checkpoints/ clip/ clip_vision/ configs/ with huggingface_hub

checkpoints/animaPencilXL_v500.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:896faa18cd6852ccf977e2dec76191c38f256d031204e233cb3ed76f6088d55b
-size 6938041144

checkpoints/flux-hyp8-Q5_K_M.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a0dac309ffb497fde0d1bbfa0291f5371d0d05c66173df830318bc475777c68a
-size 8421981408

checkpoints/flux1-dev-bnb-nf4-v2.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fef37763b8f2c8cc3463139bbb6d91aa517c605b654d4e5c540de52813f30306
-size 12044280207

checkpoints/flux1-dev.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7
-size 23802932552

checkpoints/hunyuan_dit_1.2.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787
-size 8240228270

checkpoints/juggernautXL_juggXIByRundiffusion.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:33e58e86686f6b386c526682b5da9228ead4f91d994abd4b053442dc5b42719e
-size 7105350536

checkpoints/playground-v2.5-1024px.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992
-size 6938040576

checkpoints/ponyDiffusionV6XL.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3
-size 6938041050

checkpoints/realisticStockPhoto_v20.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f99f3dec38a09b4834a4a073bdc45aabd42b422b4d327f5e8001afcb5ffb5f45
-size 6938054242

checkpoints/realisticVisionV60B1_v51VAE.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15012c538f503ce2ebfc2c8547b268c75ccdaff7a281db55399940ff1d70e21d
-size 2132625894

checkpoints/sd3_medium_incl_clips.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7f21bc5fb450220f4eb78a2f276b15422309d5166a4bdeb8c3b763a3a0581
-size 5973224240

checkpoints/sd3_medium_incl_clips_t5xxlfp16.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69a950c5d143ce782a7423c532c8a12b75da6a37b0e6f26a322acf4e76208912
-size 15761074532

checkpoints/sd3_medium_incl_clips_t5xxlfp8.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92db4295e9c9ab8401ef60566d975656a35b0bd0f6d9ce0d083725171f7b3174
-size 10867168284

clip/EVA02_CLIP_L_336_psz14_s6B.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:84c3a17a228c567a155259b2245b0b59072bf7da510260a0a02ec54de6d50b05
-size 856461210

clip/clip_l.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
-size 246144152

clip/t5xxl_fp16.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
-size 9787841024

clip/t5xxl_fp8_e4m3fn.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09
-size 4893934904

clip_vision/clip-vit-large-patch14.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1a17cdbe0f36fec524f5cafb1c261ea3bbbc13e346e0f74fc9eb0460dedd0d3
-size 1710671599

clip_vision/clip-vit-large-patch14/special_tokens_map.json

@@ -1 +0,0 @@
-{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

clip_vision/clip-vit-large-patch14/tokenizer_config.json

@@ -1,34 +0,0 @@
-{
-    "unk_token": {
-        "content": "<|endoftext|>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "bos_token": {
-        "content": "<|startoftext|>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "eos_token": {
-        "content": "<|endoftext|>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "pad_token": "<|endoftext|>",
-    "add_prefix_space": false,
-    "errors": "replace",
-    "do_lower_case": true,
-    "name_or_path": "openai/clip-vit-base-patch32",
-    "model_max_length": 77,
-    "special_tokens_map_file": "./special_tokens_map.json",
-    "tokenizer_class": "CLIPTokenizer"
-}

clip_vision/clip_vision_vit_h.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a11c14945fb98c7ac9a54fab5e498885731a0780260dad7adf41f6f59655ee5
-size 1972298538

clip_vision/model_base_caption_capfilt_large.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:96ac8749bd0a568c274ebe302b3a3748ab9be614c737f3d8c529697139174086
-size 896081425

clip_vision/wd-v1-4-moat-tagger-v2.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b8cef913be4c9e8d93f9f903e74271416502ce0b4b04df0ff1e2f00df488aa03
-size 326197340

configs/anything_v3.yaml

@@ -1,73 +0,0 @@
-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

configs/v1-inference.yaml

@@ -1,70 +0,0 @@
-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

configs/v1-inference_clip_skip_2.yaml

@@ -1,73 +0,0 @@
-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

configs/v1-inference_clip_skip_2_fp16.yaml

@@ -1,74 +0,0 @@
-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

configs/v1-inference_fp16.yaml

@@ -1,71 +0,0 @@
-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

configs/v1-inpainting-inference.yaml

@@ -1,71 +0,0 @@
-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
-

configs/v2-inference-v.yaml

@@ -1,68 +0,0 @@
-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"

configs/v2-inference-v_fp32.yaml

@@ -1,68 +0,0 @@
-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"

configs/v2-inference.yaml

@@ -1,67 +0,0 @@
-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"

configs/v2-inference_fp32.yaml

@@ -1,67 +0,0 @@
-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"

configs/v2-inpainting-inference.yaml

@@ -1,158 +0,0 @@
-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