Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+assets/image2_age_20.jpg filter=lfs diff=lfs merge=lfs -text
+assets/image2_age_50.jpg filter=lfs diff=lfs merge=lfs -text
+assets/image2_age_80.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,174 @@
+---
+license: apache-2.0
+---
+# Templates - Age Control (FLUX.2-klein-base-4B)
+
+This model is one of the Diffusion Templates series models open-sourced by [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). It allows direct control over the age of the person in the generated image by inputting the `age` parameter.
+
+## Results
+
+> **Prompt:** A portrait of a woman with black hair, wearing a suit.
+
+| Age = 20 | Age = 50 | Age = 80 |
+|:---:|:---:|:---:|
+| ![](./assets/image1_age_20.jpg) | ![](./assets/image1_age_50.jpg) | ![](./assets/image1_age_80.jpg) |
+
+---
+
+> **Prompt:** A portrait of a man, autumn park background, warm evening sunlight.
+
+| Age = 20 | Age = 50 | Age = 80 |
+|:---:|:---:|:---:|
+| ![](./assets/image2_age_20.jpg) | ![](./assets/image2_age_50.jpg) | ![](./assets/image2_age_80.jpg) |
+
+---
+A fashion portrait of an elegant woman wearing a red silk dress, high fashion photography, soft lighting. A modern minimalist living room with furniture.
+
+| Age = 20 | Age = 50 | Age = 80 |
+|:---:|:---:|:---:|
+| ![](./assets/image3_age_20.jpg) | ![](./assets/image3_age_50.jpg) | ![](./assets/image3_age_80.jpg) |
+
+## Inference Code
+
+* Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
+
+```
+git clone https://github.com/modelscope/DiffSynth-Studio.git
+cd DiffSynth-Studio
+pip install -e .
+```
+
+* Direct inference (requires 40GB GPU memory)
+
+```python
+from diffsynth.diffusion.template import TemplatePipeline
+from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
+import torch
+```
+
+pipe = Flux2ImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),
+)
+template = TemplatePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-Age")],
+)
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 20}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_20.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 50}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_50.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 80}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_80.jpg")
+```
+
+* Enable lazy loading and memory management, requires 24G GPU memory
+
+```python
+from diffsynth.diffusion.template import TemplatePipeline
+from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
+import torch
+
+```python
+vram_config = {
+    "offload_dtype": "disk",
+    "offload_device": "disk",
+    "onload_dtype": torch.float8_e4m3fn,
+    "onload_device": "cpu",
+    "preparing_dtype": torch.float8_e4m3fn,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = Flux2ImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors", **vram_config),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors", **vram_config),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),
+    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
+)
+template = TemplatePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-Age")],
+    lazy_loading=True,
+)
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 20}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_20.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 50}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_50.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 80}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_80.jpg")
+```
+
+## Training Code
+
+After installing DiffSynth-Studio, use the following script to start training. For more information, please refer to the [DiffSynth-Studio Documentation](https://diffsynth-studio-doc.readthedocs.io/zh-cn/latest/).
+
+```shell
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/Template-KleinBase4B-Age/*" --local_dir ./data/diffsynth_example_dataset
+
+accelerate launch examples/flux2/model_training/train.py \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/Template-KleinBase4B-Age \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/Template-KleinBase4B-Age/metadata.jsonl \
+  --extra_inputs "template_inputs" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
+  --template_model_id_or_path "DiffSynth-Studio/Template-KleinBase4B-Age:" \
+  --tokenizer_path "black-forest-labs/FLUX.2-klein-4B:tokenizer/" \
+  --learning_rate 1e-4 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.template_model." \
+  --output_path "./models/train/Template-KleinBase4B-Age_full" \
+  --trainable_models "template_model" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters
+```

README_from_modelscope.md

@@ -0,0 +1,178 @@
+---
+frameworks:
+- Pytorch
+license: Apache License 2.0
+tags: []
+tasks:
+- text-to-image-synthesis
+---
+
+# Templates-年龄控制（FLUX.2-klein-base-4B）
+
+本模型是 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) 开源的 Diffusion Templates 系列模型之一。该模型能够通过直接输入 `age` 参数，控制生成图像中人物的年龄。
+
+## 效果展示
+
+> **Prompt:** A portrait of a woman with black hair, wearing a suit.
+
+| Age = 20 | Age = 50 | Age = 80 |
+|:---:|:---:|:---:|
+| ![](./assets/image1_age_20.jpg) | ![](./assets/image1_age_50.jpg) | ![](./assets/image1_age_80.jpg) |
+
+---
+
+> **Prompt:** A portrait of a man, autumn park background, warm evening sunlight.
+
+| Age = 20 | Age = 50 | Age = 80 |
+|:---:|:---:|:---:|
+| ![](./assets/image2_age_20.jpg) | ![](./assets/image2_age_50.jpg) | ![](./assets/image2_age_80.jpg) |
+
+---
+A fashion portrait of an elegant woman wearing a red silk dress, high fashion photography, soft lighting.A modern minimalist living room with furniture.
+
+| Age = 20 | Age = 50 | Age = 80 |
+|:---:|:---:|:---:|
+| ![](./assets/image3_age_20.jpg) | ![](./assets/image3_age_50.jpg) | ![](./assets/image3_age_80.jpg) |
+
+## 推理代码
+
+* 安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
+
+```
+git clone https://github.com/modelscope/DiffSynth-Studio.git
+cd DiffSynth-Studio
+pip install -e .
+```
+
+* 直接推理，需 40G 显存
+
+```python
+from diffsynth.diffusion.template import TemplatePipeline
+from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
+import torch
+
+pipe = Flux2ImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),
+)
+template = TemplatePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-Age")],
+)
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 20}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_20.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 50}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_50.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 80}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_80.jpg")
+```
+
+* 开启惰性加载和显存管理，需 24G 显存
+
+```python
+from diffsynth.diffusion.template import TemplatePipeline
+from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
+import torch
+
+vram_config = {
+    "offload_dtype": "disk",
+    "offload_device": "disk",
+    "onload_dtype": torch.float8_e4m3fn,
+    "onload_device": "cpu",
+    "preparing_dtype": torch.float8_e4m3fn,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = Flux2ImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors", **vram_config),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors", **vram_config),
+        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),
+    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
+)
+template = TemplatePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-Age")],
+    lazy_loading=True,
+)
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 20}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_20.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 50}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_50.jpg")
+image = template(
+    pipe,
+    prompt="A portrait of a woman with black hair, wearing a suit.",
+    seed=0, cfg_scale=4, num_inference_steps=50,
+    template_inputs=[{"age": 80}],
+    negative_template_inputs=[{"age": 45}],
+)
+image.save(f"image_age_80.jpg")
+```
+
+## 训练代码
+
+安装 DiffSynth-Studio 后，使用以下脚本可开启训练，更多信息请参考 [DiffSynth-Studio 文档](https://diffsynth-studio-doc.readthedocs.io/zh-cn/latest/)。
+
+```shell
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/Template-KleinBase4B-Age/*" --local_dir ./data/diffsynth_example_dataset
+
+accelerate launch examples/flux2/model_training/train.py \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/Template-KleinBase4B-Age \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/Template-KleinBase4B-Age/metadata.jsonl \
+  --extra_inputs "template_inputs" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
+  --template_model_id_or_path "DiffSynth-Studio/Template-KleinBase4B-Age:" \
+  --tokenizer_path "black-forest-labs/FLUX.2-klein-4B:tokenizer/" \
+  --learning_rate 1e-4 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.template_model." \
+  --output_path "./models/train/Template-KleinBase4B-Age_full" \
+  --trainable_models "template_model" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters
+```

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-to-image-synthesis"}

model.py

@@ -0,0 +1,60 @@
+import torch, math
+from PIL import Image
+import numpy as np
+
+
+class SingleValueEncoder(torch.nn.Module):
+    def __init__(self, dim_in=256, dim_out=4096, length=32):
+        super().__init__()
+        self.length = length
+        self.prefer_value_embedder = torch.nn.Sequential(torch.nn.Linear(dim_in, dim_out), torch.nn.SiLU(), torch.nn.Linear(dim_out, dim_out))
+        self.positional_embedding = torch.nn.Parameter(torch.randn(self.length, dim_out))
+
+    def get_timestep_embedding(self, timesteps, embedding_dim, max_period=10000):
+        half_dim = embedding_dim // 2
+        exponent = -math.log(max_period) * torch.arange(0, half_dim, dtype=torch.float32, device=timesteps.device) / half_dim
+        emb = timesteps[:, None].float() * torch.exp(exponent)[None, :]
+        emb = torch.cat([torch.cos(emb), torch.sin(emb)], dim=-1)
+        return emb
+
+    def forward(self, value, dtype):
+        emb = self.get_timestep_embedding(value * 10, 256).to(dtype)
+        emb = self.prefer_value_embedder(emb).squeeze(0)
+        base_embeddings = emb.expand(self.length, -1)
+        positional_embedding = self.positional_embedding.to(dtype=base_embeddings.dtype, device=base_embeddings.device)
+        learned_embeddings = base_embeddings + positional_embedding
+        return learned_embeddings
+
+
+class ValueFormatModel(torch.nn.Module):
+    def __init__(self, num_double_blocks=5, num_single_blocks=20, dim=3072, num_heads=24, length=512):
+        super().__init__()
+        self.block_names = [f"double_{i}" for i in range(num_double_blocks)] + [f"single_{i}" for i in range(num_single_blocks)]
+        self.proj_k = torch.nn.ModuleDict({block_name: SingleValueEncoder(dim_out=dim, length=length) for block_name in self.block_names})
+        self.proj_v = torch.nn.ModuleDict({block_name: SingleValueEncoder(dim_out=dim, length=length) for block_name in self.block_names})
+        self.num_heads = num_heads
+        self.length = length
+
+    @torch.no_grad()
+    def process_inputs(self, pipe, age, **kwargs):
+        return {"value": torch.Tensor([age]).to(dtype=pipe.torch_dtype, device=pipe.device)}
+
+    def forward(self, value, **kwargs):
+        kv_cache = {}
+        for block_name in self.block_names:
+            k = self.proj_k[block_name](value, value.dtype)
+            k = k.view(1, self.length, self.num_heads, -1)
+            v = self.proj_v[block_name](value, value.dtype)
+            v = v.view(1, self.length, self.num_heads, -1)
+            kv_cache[block_name] = (k, v)
+        return {"kv_cache": kv_cache}
+
+
+class DataAnnotator:
+    def __call__(self, age, **kwargs):
+        return {"age": age}
+
+
+TEMPLATE_MODEL = ValueFormatModel
+TEMPLATE_MODEL_PATH = "model.safetensors"
+TEMPLATE_DATA_PROCESSOR = DataAnnotator

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f30866638a48ffe5cf3d1524ec74c66d6ab9414176ec1ff371a9b51cf17ddf
+size 1180292000