|
--- |
|
datasets: |
|
- cookey39/blue_reflection |
|
language: |
|
- en |
|
--- |
|
|
|
# SDXL LoRA DreamBooth - cookey39/reflector |
|
|
|
### Examples: |
|
|
|
https://www.pixiv.net/artworks/119270564 |
|
|
|
https://www.pixiv.net/artworks/119269797 |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
### These are cookey39/reflector LoRA adaption weights for cookey39/hyper-sd-8step. |
|
|
|
## Download model |
|
|
|
### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke |
|
|
|
- **LoRA**: download **[`reflector.safetensors` here 💾](/cookey39/reflector/blob/main/reflector.safetensors)**. |
|
- Place it on your `models/Lora` folder. |
|
- On AUTOMATIC1111, load the LoRA by adding `<lora:reflector:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/). |
|
- *Embeddings*: download **[`reflector_emb.safetensors` here 💾](/cookey39/reflector/blob/main/reflector_emb.safetensors)**. |
|
- Place it on it on your `embeddings` folder |
|
- Use it by adding `reflector_emb` to your prompt. For example, `blue_reflection:` |
|
(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 |
|
from diffusers import DiffusionPipeline, DDIMScheduler |
|
import torch |
|
from huggingface_hub import hf_hub_download |
|
from safetensors.torch import load_file |
|
|
|
pipeline = AutoPipelineForText2Image.from_pretrained('cookey39/reflector', torch_dtype=torch.float16).to('cuda') |
|
|
|
# lower eta results in more detail |
|
instance_token = "<s0><s1>" |
|
prompt = f"a {instance_token}masterpiece, best quality,long hair, cute face, white kneehighs, black hair, hair strand, twin braids, cat hair ornament, adorable girl, absurdres, huge_filesize, Japanese, game_cg, {instance_token} " |
|
negative_prompt = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bad feet, " |
|
image = pipeline(prompt=prompt, negative_prompt = negative_prompt, num_inference_steps=50, cross_attention_kwargs={"scale": 1.0},width = 720, height=1080).images[0] |
|
image |
|
``` |
|
|
|
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](/cookey39/reflector/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_sdxl_advanced.py). |
|
|
|
LoRA for the text encoder was enabled. False. |
|
|
|
Pivotal tuning was enabled: True. |
|
|
|
Special VAE used for training: None. |
