Stable Conceptualizer Inference
hf-notebooksdiffusers
Export
Stable Conceptualizer - Stable Diffusion using learned concepts
The Stable Conceptualizer enables you to use pre-learned concepts on Stable Diffusion via textual-inversion using ๐ค Hugging Face ๐งจ Diffusers library.
Navigate the library of pre-learned concepts here. For teaching the model new concepts using Textual Inversion, use this notebook.
Initial setup
[1]
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ 934.9/934.9 kB 13.5 MB/s eta 0:00:00 โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ 7.0/7.0 MB 52.7 MB/s eta 0:00:00 โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ 53.1/53.1 kB 5.3 MB/s eta 0:00:00 โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ 219.1/219.1 kB 15.2 MB/s eta 0:00:00 โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ 224.5/224.5 kB 3.2 MB/s eta 0:00:00 โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ 7.8/7.8 MB 55.5 MB/s eta 0:00:00
[2]
VBox(children=(HTML(value='<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svโฆ
[3]
Run Stable Diffusion with pre-trained Learned Concepts
If you want to teach Stable Diffusion your own concepts, use this notebook.
[4]
pretrained_model_name_or_path
[5]
repo_id_embeds
Downloading learned_embeds.bin: 0%| | 0.00/3.82k [00:00<?, ?B/s]
Downloading (โฆ)token_identifier.txt: 0%| | 0.00/9.00 [00:00<?, ?B/s]
The placeholder token for your concept is <cat-toy>
[11]
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
[12]
[9]
prompt
num_samples
num_rows
0%| | 0/50 [00:00<?, ?it/s]
0%| | 0/50 [00:00<?, ?it/s]