File size: 5,273 Bytes
ac788e5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
---
library_name: Diffusers
base_model:
- black-forest-labs/FLUX.2-dev
---
This tiny model is for debugging. It is randomly initialized with the config adapted from [black-forest-labs/FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev).
File size:
- 2MB text_encoder/model.safetensors
- 0.9MB transformer/diffusion_pytorch_model.safetensors
- 0.5MB vae/diffusion_pytorch_model.safetensors
### Example usage:
```python
import io
import requests
import torch
from diffusers import Flux2Pipeline
from diffusers.utils import load_image
from huggingface_hub import get_token
model_id = "yujiepan/flux.2-tiny-random"
device = "cuda:0"
torch_dtype = torch.bfloat16
pipe = Flux2Pipeline.from_pretrained(
model_id, torch_dtype=torch_dtype
).to(device)
prompt = "Realistic macro photograph of a hermit crab using a soda can as its shell"
cat_image = load_image(
"https://huggingface.co/spaces/zerogpu-aoti/FLUX.1-Kontext-Dev-fp8-dynamic/resolve/main/cat.png")
image = pipe(
prompt=prompt,
image=[cat_image], # optional multi-image input
generator=torch.Generator(device=device).manual_seed(42),
num_inference_steps=4,
guidance_scale=4,
text_encoder_out_layers=(1,),
).images[0]
print(image)
```
### Codes to create this repo:
```python
import json
import torch
from diffusers import (
AutoencoderKLFlux2,
FlowMatchEulerDiscreteScheduler,
Flux2Pipeline,
Flux2Transformer2DModel,
)
from huggingface_hub import hf_hub_download
from transformers import (
AutoConfig,
AutoTokenizer,
Mistral3ForConditionalGeneration,
PixtralProcessor,
)
from transformers.generation import GenerationConfig
source_model_id = "black-forest-labs/FLUX.2-dev"
save_folder = "/tmp/yujiepan/flux.2-tiny-random"
torch.set_default_dtype(torch.bfloat16)
scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(
source_model_id, subfolder='scheduler')
tokenizer = PixtralProcessor.from_pretrained(
source_model_id, subfolder='tokenizer')
def save_json(path, obj):
import json
from pathlib import Path
Path(path).parent.mkdir(parents=True, exist_ok=True)
with open(path, 'w', encoding='utf-8') as f:
json.dump(obj, f, indent=2, ensure_ascii=False)
def init_weights(model):
import torch
from transformers import set_seed
set_seed(42)
model = model.cpu()
with torch.no_grad():
for name, p in sorted(model.named_parameters()):
torch.nn.init.normal_(p, 0, 0.1)
print(name, p.shape, p.dtype, p.device)
with open(hf_hub_download(source_model_id, filename='text_encoder/config.json', repo_type='model'), 'r', encoding='utf - 8') as f:
config = json.load(f)
config['text_config'].update({
'hidden_size': 8,
'intermediate_size': 64,
"head_dim": 32,
'num_attention_heads': 8,
'num_hidden_layers': 2,
'num_key_value_heads': 4,
'tie_word_embeddings': True,
})
config['vision_config'].update(
{
"head_dim": 32,
"hidden_size": 32,
"intermediate_size": 64,
"num_attention_heads": 1,
"num_hidden_layers": 2,
}
)
save_json(f'{save_folder}/text_encoder/config.json', config)
text_encoder_config = AutoConfig.from_pretrained(
f'{save_folder}/text_encoder')
text_encoder = Mistral3ForConditionalGeneration(
text_encoder_config).to(torch.bfloat16)
generation_config = GenerationConfig.from_pretrained(
source_model_id, subfolder='text_encoder')
# text_encoder.config.generation_config = generation_config
text_encoder.generation_config = generation_config
init_weights(text_encoder)
with open(hf_hub_download(source_model_id, filename='transformer/config.json', repo_type='model'), 'r', encoding='utf-8') as f:
config = json.load(f)
config.update({
'attention_head_dim': 32,
"in_channels": 32,
'axes_dims_rope': [8, 12, 12],
'joint_attention_dim': 8,
'num_attention_heads': 2,
'num_layers': 2,
'num_single_layers': 2,
})
save_json(f'{save_folder}/transformer/config.json', config)
transformer_config = Flux2Transformer2DModel.load_config(
f'{save_folder}/transformer')
transformer = Flux2Transformer2DModel.from_config(transformer_config)
init_weights(transformer)
with open(hf_hub_download(source_model_id, filename='vae/config.json', repo_type='model'), 'r', encoding='utf-8') as f:
config = json.load(f)
config.update({
'layers_per_block': 1,
'block_out_channels': [32, 32],
'latent_channels': 8,
'down_block_types': ['DownEncoderBlock2D', 'DownEncoderBlock2D'],
'up_block_types': ['UpDecoderBlock2D', 'UpDecoderBlock2D']
})
save_json(f'{save_folder}/vae/config.json', config)
vae_config = AutoencoderKLFlux2.load_config(f'{save_folder}/vae')
vae = AutoencoderKLFlux2.from_config(vae_config)
init_weights(vae)
pipeline = Flux2Pipeline(
scheduler=scheduler,
text_encoder=text_encoder,
tokenizer=tokenizer,
transformer=transformer,
vae=vae,
)
pipeline = pipeline.to(torch.bfloat16)
pipeline.save_pretrained(save_folder, safe_serialization=True)
print(pipeline)
``` |