awoo

Signed-off-by: Balazs Horvath <acsipont@gmail.com>

jtp2.py

@@ -1,161 +0,0 @@
-import os
-import json
-from PIL import Image
-import safetensors.torch
-import timm
-from timm.models import VisionTransformer
-import torch
-from torchvision.transforms import transforms
-from torchvision.transforms import InterpolationMode
-import torchvision.transforms.functional as TF
-import argparse
-import pillow_jxl
-
-torch.set_grad_enabled(False)
-
-class Fit(torch.nn.Module):
-    def __init__(self, bounds: tuple[int, int] | int, interpolation=InterpolationMode.LANCZOS, grow: bool = True, pad: float | None = None):
-        super().__init__()
-        self.bounds = (bounds, bounds) if isinstance(bounds, int) else bounds
-        self.interpolation = interpolation
-        self.grow = grow
-        self.pad = pad
-
-    def forward(self, img: Image) -> Image:
-        wimg, himg = img.size
-        hbound, wbound = self.bounds
-        hscale = hbound / himg
-        wscale = wbound / wimg
-        if not self.grow:
-            hscale = min(hscale, 1.0)
-            wscale = min(wscale, 1.0)
-        scale = min(hscale, wscale)
-        if scale == 1.0:
-            return img
-        hnew = min(round(himg * scale), hbound)
-        wnew = min(round(wimg * scale), wbound)
-        img = TF.resize(img, (hnew, wnew), self.interpolation)
-        if self.pad is None:
-            return img
-        hpad = hbound - hnew
-        wpad = wbound - wnew
-        tpad = hpad // 2
-        bpad = hpad - tpad
-        lpad = wpad // 2
-        rpad = wpad - lpad
-        return TF.pad(img, (lpad, tpad, rpad, bpad), self.pad)
-
-    def __repr__(self) -> str:
-        return f"{self.__class__.__name__}(bounds={self.bounds}, interpolation={self.interpolation.value}, grow={self.grow}, pad={self.pad})"
-
-class CompositeAlpha(torch.nn.Module):
-    def __init__(self, background: tuple[float, float, float] | float):
-        super().__init__()
-        self.background = (background, background, background) if isinstance(background, float) else background
-        self.background = torch.tensor(self.background).unsqueeze(1).unsqueeze(2)
-
-    def forward(self, img: torch.Tensor) -> torch.Tensor:
-        if img.shape[-3] == 3:
-            return img
-        alpha = img[..., 3, None, :, :]
-        img[..., :3, :, :] *= alpha
-        background = self.background.expand(-1, img.shape[-2], img.shape[-1])
-        if background.ndim == 1:
-            background = background[:, None, None]
-        elif background.ndim == 2:
-            background = background[None, :, :]
-        img[..., :3, :, :] += (1.0 - alpha) * background
-        return img[..., :3, :, :]
-
-    def __repr__(self) -> str:
-        return f"{self.__class__.__name__}(background={self.background})"
-
-transform = transforms.Compose([
-    Fit((384, 384)),
-    transforms.ToTensor(),
-    CompositeAlpha(0.5),
-    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5], inplace=True),
-    transforms.CenterCrop((384, 384)),
-])
-
-model = timm.create_model("vit_so400m_patch14_siglip_384.webli", pretrained=False, num_classes=9083)  # type: VisionTransformer
-
-class GatedHead(torch.nn.Module):
-    def __init__(self, num_features: int, num_classes: int):
-        super().__init__()
-        self.num_classes = num_classes
-        self.linear = torch.nn.Linear(num_features, num_classes * 2)
-        self.act = torch.nn.Sigmoid()
-        self.gate = torch.nn.Sigmoid()
-
-    def forward(self, x: torch.Tensor) -> torch.Tensor:
-        x = self.linear(x)
-        x = self.act(x[:, :self.num_classes]) * self.gate(x[:, self.num_classes:])
-        return x
-
-model.head = GatedHead(min(model.head.weight.shape), 9083)
-safetensors.torch.load_model(model, "JTP_PILOT2-e3-vit_so400m_patch14_siglip_384.safetensors")
-
-if torch.cuda.is_available():
-    model.cuda()
-    if torch.cuda.get_device_capability()[0] >= 7:  # tensor cores
-        model.to(dtype=torch.float16, memory_format=torch.channels_last)
-
-model.eval()
-
-with open("tags.json", "r") as file:
-    tags = json.load(file)  # type: dict
-allowed_tags = list(tags.keys())
-
-for idx, tag in enumerate(allowed_tags):
-    allowed_tags[idx] = tag.replace("_", " ")
-
-sorted_tag_score = {}
-
-def run_classifier(image, threshold):
-    global sorted_tag_score
-    img = image.convert('RGBA')
-    tensor = transform(img).unsqueeze(0)
-    if torch.cuda.is_available():
-        tensor = tensor.cuda()
-        if torch.cuda.get_device_capability()[0] >= 7:  # tensor cores
-            tensor = tensor.to(dtype=torch.float16, memory_format=torch.channels_last)
-    with torch.no_grad():
-        probits = model(tensor)[0].cpu()
-        values, indices = probits.topk(250)
-    tag_score = dict()
-    for i in range(indices.size(0)):
-        tag_score[allowed_tags[indices[i]]] = values[i].item()
-    sorted_tag_score = dict(sorted(tag_score.items(), key=lambda item: item[1], reverse=True))
-    return create_tags(threshold)
-
-def create_tags(threshold):
-    global sorted_tag_score
-    filtered_tag_score = {key: value for key, value in sorted_tag_score.items() if value > threshold}
-    text_no_impl = ", ".join(filtered_tag_score.keys())
-    return text_no_impl, filtered_tag_score
-
-def process_directory(directory, threshold):
-    results = {}
-    for root, _, files in os.walk(directory):
-        for file in files:
-            if file.lower().endswith(('.jpg', '.jpeg', '.png', '.jxl')):
-                image_path = os.path.join(root, file)
-                image = Image.open(image_path)
-                tags, _ = run_classifier(image, threshold)
-                results[image_path] = tags
-                # Save tags to a text file with the same name as the image
-                text_file_path = os.path.splitext(image_path)[0] + ".txt"
-                with open(text_file_path, "w") as text_file:
-                    text_file.write(tags)
-    return results
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run inference on a directory of images.")
-    parser.add_argument("directory", type=str, help="Target directory containing images.")
-    parser.add_argument("--threshold", type=float, default=0.2, help="Threshold for tag filtering.")
-    args = parser.parse_args()
-
-    results = process_directory(args.directory, args.threshold)
-    for image_path, tags in results.items():
-        print(f"{image_path}: {tags}")

metrics/by_dagasi-v220240731004448/network_train/events.out.tfevents.1722379588.berilia.2834308.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9ccee82a99379d3deeea818c60394392931cfff3fe19fa7483dc6ad0fe3f5568
-size 403320

metrics/by_hax-v1e400-20240804130227/network_train/events.out.tfevents.1722769396.berilia.3289669.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:034baf9175755f1a4d71e099eef11c13eaaf4f20f784c7b9ff121342ef5c7ddb
-size 396905

metrics/by_jinxit-v2e400-20240729235422/network_train/events.out.tfevents.1722290163.berilia.3199627.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2c46a98e965052fabfbc1b65bfd9290e33e1358a3cf7c4b26addd2a627114595
-size 843874

metrics/magic-normalized-v2e400-20240730013158/network_train/events.out.tfevents.1722295954.berilia.3268268.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a24bc14ad339847b995826600261af14c07c923a4fc04248b7124d25fadce7c8
-size 544162

metrics/realistic-v7e400-20240802163709/network_train/events.out.tfevents.1722609499.berilia.1601635.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:55b3897bb017c365e498cb9545186be2243474821719180fb2fb5c519273d193
-size 820965

metrics/space-v2e200-20240730174030/network_train/events.out.tfevents.1722354067.berilia.1646768.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2288178ab681b4b4a20b12a65fe2627426add1bc4562530230952833ebb7950
-size 620514

metrics/stoat-v7e400-20240729181527/network_train/events.out.tfevents.1722269758.berilia.2962309.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8d5a441c2f829509ff64f2ef9ee575c93fef551944b85f81214fef7bb98a06ed
-size 806521

train-pony.sh

@@ -1,103 +0,0 @@
-#/usr/bin/env zsh
-
-NAME="stoat-v2s400"
-
-# alpha=1 @ dim=16 is the same lr than alpha=4 @ dim=256
-# --min_snr_gamma=1
-
-args=(
-    --pretrained_model_name_or_path=/home/kade/ComfyUI/models/checkpoints/ponyDiffusionV6XL_v6StartWithThisOne.safetensors
-    # Output, logging
-    --output_dir="/home/kade/output_dir/$NAME"
-    --output_name="$NAME"
-    --log_prefix="$NAME-"
-    --log_with=tensorboard
-    --logging_dir=/home/kade/output_dir/logs
-    --seed=1728871242
-
-    # Dataset
-    --train_data_dir=/home/kade/training_dir
-    --dataset_repeats=1
-    --resolution="1024,1024"
-    --enable_bucket
-    --bucket_reso_steps=32
-    --min_bucket_reso=256
-    --max_bucket_reso=2048
-    --flip_aug
-    --shuffle_caption
-    --cache_latents
-    --cache_latents_to_disk
-    --max_data_loader_n_workers=8
-    --persistent_data_loader_workers
-
-    # Network config
-    --network_dim=8
-    --network_alpha=4
-    --network_module="lycoris.kohya"
-    --network_args
-               "preset=full"
-               "conv_dim=256"
-               "conv_alpha=4"
-               "rank_dropout=0"
-               "module_dropout=0"
-               "use_tucker=False"
-               "use_scalar=False"
-               "rank_dropout_scale=False"
-               "algo=locon"
-               "dora_wd=False"
-               "train_norm=False"
-    --network_dropout=0
-
-    # Optimizer config
-    --optimizer_type=ClybW
-    --train_batch_size=8
-    --gradient_accumulation_steps=6
-    --max_grad_norm=1
-    --gradient_checkpointing
-    #--lr_warmup_steps=6
-    #--scale_weight_norms=1
-
-    # LR Scheduling
-    --max_train_steps=400
-    --learning_rate=0.0002
-    --unet_lr=0.0002
-    --text_encoder_lr=0.0001
-    --lr_scheduler="cosine"
-    --lr_scheduler_args="num_cycles=0.375"
-
-    # Noise
-    --multires_noise_iterations=12
-    --multires_noise_discount=0.4
-    #--min_snr_gamma=1
-
-    # Optimization, details
-    --no_half_vae
-    --sdpa
-    --mixed_precision="bf16"
-
-    # Saving
-    --save_model_as="safetensors"
-    --save_precision="fp16"
-    --save_every_n_steps=20
-    --save_state
-    # Either resume from a saved state
-    #--resume="$HOME/output_dir/wolflink-vfucks400" # Resume from saved state
-    #--skip_until_initial_step
-    # Or from a checkpoint
-    #--network_weights="$HOME/output_dir/wolflink-vfucks400/wolflink-vfucks400-step00000120.safetensors" # Resume from checkpoint (not needed with state, i think)
-    #--initial_step=120
-
-    # Sampling
-    --sample_every_n_steps=20
-    --sample_prompts=/home/kade/training_dir/sample-prompts.txt
-    --sample_sampler="euler_a"
-    --caption_extension=".txt"
-)
-
-
-cd ~/source/repos/sd-scripts
-
-#accelerate launch --num_cpu_threads_per_process=2  
-python "./sdxl_train_network.py" "${args[@]}"
-
-cd ~