Upload 6 files

animefull-final-pruned/config.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: 512
+          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

animefull-final-pruned/model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d59c3dde4c56c6d5c41da34cc55ce479d93b4007046980934b14db71bdb2a8
+size 4265377440

sd-prune/anime700k-64bs-0.1ucg-penultimate-1epoch-clip-ema-continue-76000-ema-pruned.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939269be42067dc822b206b2fada2947a5c20e896059036705b56d68236bd7ef
+size 2132882528

sd-prune/anime700k-64bs-0.1ucg-penultimate-1epoch-clip-ema-continue-76000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828a21b769b3a32b1508f3b47828fc9d7c27c14a0cab64bc42fb785cd24211a6
+size 7703828146

sd-prune/prune.py

@@ -0,0 +1,65 @@
+import os
+import torch
+
+
+def prune_it(p, keep_only_ema=True):
+    print(f"prunin' in path: {p}")
+    size_initial = os.path.getsize(p)
+    nsd = dict()
+    sd = torch.load(p, map_location="cpu")
+    print(sd.keys())
+    #for k in sd.keys():
+    #    if k != "optimizer_states":
+    #        nsd[k] = sd[k]
+    #else:
+    #    print(f"removing optimizer states for path {p}")
+    if "global_step" in sd:
+        print(f"This is global step {sd['global_step']}.")
+    if keep_only_ema:
+        if "state_dict" in sd:
+            sd = sd["state_dict"]
+        # infer ema keys
+        ema_keys = {k: "model_ema." + k[6:].replace(".", ".") for k in sd.keys() if k.startswith("model.")}
+        new_sd = {"state_dict": {}}
+
+        for k in sd:
+            ema_k = "___"
+            try:
+                ema_k = "model_ema." + k[6:].replace(".", "")
+            except:
+                pass
+            if ema_k in sd:
+                new_sd[k] = sd[ema_k]#.half()
+                print("ema: " + ema_k + " > " + k)
+            elif not k.startswith("model_ema.") or k in ["model_ema.num_updates", "model_ema.decay"]:
+                new_sd[k] = sd[k]#.half()
+                print(k)
+            else:
+                print("skipped: " + k)
+            if k in new_sd and isinstance(new_sd[k], torch.FloatTensor):
+                new_sd[k] = new_sd[k]#.half()
+
+        #assert len(new_sd) == len(sd) - len(ema_keys)
+        nsd["state_dict"] = new_sd
+    else:
+        sd = nsd['state_dict'].copy()
+        new_sd = dict()
+        for k in sd:
+            new_sd[k] = sd[k]#.half()
+        nsd['state_dict'] = new_sd
+
+    fn = f"{os.path.splitext(p)[0]}-pruned.ckpt" if not keep_only_ema else f"{os.path.splitext(p)[0]}-ema-pruned.ckpt"
+    print(f"saving pruned checkpoint at: {fn}")
+    torch.save(nsd, fn)
+    newsize = os.path.getsize(fn)
+    MSG = f"New ckpt size: {newsize*1e-9:.2f} GB. " + \
+          f"Saved {(size_initial - newsize)*1e-9:.2f} GB by removing optimizer states"
+    if keep_only_ema:
+        MSG += " and non-EMA weights"
+    print(MSG)
+
+
+if __name__ == "__main__":
+    #prune_it('anime700k-64bs-0.1ucg-penultimate-1epoch-clip-ema-continue-76000.pt')
+    import sys
+    prune_it(sys.argv[1])

vector_adjust/v2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac22b73b16510d16b8480a1a0d6c487556eac7eda0b6c9436ba862d8f22139ca
+size 2953951