|
--- |
|
base_model: stabilityai/stable-diffusion-2-1 |
|
library_name: diffusers |
|
license: openrail++ |
|
inference: true |
|
instance_prompt: a red chicken in the style of <s0><s1> |
|
widget: |
|
- text: a <s0><s1> chicken on a beach, in the style of <s0><s1> |
|
output: |
|
url: image_0.png |
|
- text: a <s0><s1> chicken on a beach, in the style of <s0><s1> |
|
output: |
|
url: image_1.png |
|
- text: a <s0><s1> chicken on a beach, in the style of <s0><s1> |
|
output: |
|
url: image_2.png |
|
- text: a <s0><s1> chicken on a beach, in the style of <s0><s1> |
|
output: |
|
url: image_3.png |
|
tags: |
|
- text-to-image |
|
- diffusers |
|
- diffusers-training |
|
- lora |
|
- template:sd-lorastable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
- diffusers |
|
- diffusers-training |
|
- lora |
|
- template:sd-lorastable-diffusion |
|
- stable-diffusion-diffusers |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the training script had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# SD1.5 LoRA DreamBooth - cindyloo337/sbne-chicken-sd21-lora |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
### These are cindyloo337/sbne-chicken-sd21-lora LoRA adaption weights for stabilityai/stable-diffusion-2-1. |
|
|
|
## Download model |
|
|
|
### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke |
|
|
|
- **LoRA**: download **[`sbne-chicken-sd21-lora.safetensors` here 💾](/cindyloo337/sbne-chicken-sd21-lora/blob/main/sbne-chicken-sd21-lora.safetensors)**. |
|
- Place it on your `models/Lora` folder. |
|
- On AUTOMATIC1111, load the LoRA by adding `<lora:sbne-chicken-sd21-lora:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/). |
|
- *Embeddings*: download **[`sbne-chicken-sd21-lora_emb.safetensors` here 💾](/cindyloo337/sbne-chicken-sd21-lora/blob/main/sbne-chicken-sd21-lora_emb.safetensors)**. |
|
- Place it on it on your `embeddings` folder |
|
- Use it by adding `sbne-chicken-sd21-lora_emb` to your prompt. For example, `a red chicken in the style of sbne-chicken-sd21-lora_emb` |
|
(you need both the LoRA and the embeddings as they were trained together for this LoRA) |
|
|
|
|
|
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) |
|
|
|
```py |
|
from diffusers import AutoPipelineForText2Image |
|
import torch |
|
from huggingface_hub import hf_hub_download |
|
from safetensors.torch import load_file |
|
|
|
pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda') |
|
pipeline.load_lora_weights('cindyloo337/sbne-chicken-sd21-lora', weight_name='pytorch_lora_weights.safetensors') |
|
embedding_path = hf_hub_download(repo_id='cindyloo337/sbne-chicken-sd21-lora', filename='sbne-chicken-sd21-lora_emb.safetensors', repo_type="model") |
|
state_dict = load_file(embedding_path) |
|
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer) |
|
|
|
image = pipeline('a <s0><s1> chicken on a beach, in the style of <s0><s1>').images[0] |
|
``` |
|
|
|
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) |
|
|
|
## Trigger words |
|
|
|
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens: |
|
|
|
to trigger concept `TOK` → use `<s0><s1>` in your prompt |
|
|
|
|
|
|
|
## Details |
|
All [Files & versions](/cindyloo337/sbne-chicken-sd21-lora/tree/main). |
|
|
|
The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py). |
|
|
|
LoRA for the text encoder was enabled. False. |
|
|
|
Pivotal tuning was enabled: True. |
|
|
|
Special VAE used for training: None. |
|
|
|
|
|
|
|
## Intended uses & limitations |
|
|
|
#### How to use |
|
|
|
```python |
|
# TODO: add an example code snippet for running this diffusion pipeline |
|
``` |
|
|
|
#### Limitations and bias |
|
|
|
[TODO: provide examples of latent issues and potential remediations] |
|
|
|
## Training details |
|
|
|
[TODO: describe the data used to train the model] |
