|
--- |
|
license: mit |
|
language: |
|
- en |
|
library_name: diffusers |
|
tags: |
|
- lora |
|
- text-to-image |
|
base_model: "stabilityai/stable-diffusion-xl-base-1.0" |
|
--- |
|
|
|
# Mann-E Turbo |
|
|
|
This is a part of _Mann-E Community Edition_ models. This model is a basic implementation of [Mann-E](https://mann-e.com)'s original model (which is not Stable Diffusion anymore) as a LoRa for SDXL. Since the whole business of Mann-E started around SD ecosystem, we've decided to release our LoRa for SD users and people who enjoy using models locally! |
|
|
|
## Sample Generations |
|
|
|
<div style="text-align:center;"> |
|
|
|
<img src="./hf-1.png" width=512 height=512> |
|
|
|
<img src="./hf-2.png" width=512 height=512> |
|
|
|
<img src="./hf-3.png" width=512 height=512> |
|
|
|
<img src="./hf-4.png" width=512 height=512> |
|
|
|
</div> |
|
|
|
## Considerations |
|
|
|
- Model __IS__ capable of making accidental and intentional _NSFW_ material. So be careful while using the LoRa in presence of people who might be sensitive to this material. |
|
- The model has tested with SDXL 1.0, SDXL Turbo and even SDXL Lightning models and it works perfectly. |
|
- We've tested the model with A111 and `diffusers`. For ComfyUI, we may need contributions if it doesn't work. |
|
- DreamShaperXL, TurboVisioXL and RealVis were models with the best results. You may consider using them or merges/fine-tunes based on those! |
|
- This LoRa is compatible with other LoRa's as well. Be careful to weight it exactly 1 to get results like what we're presenting here. |
|
- DPM SDE++ Karras is the best scheduler. 6-10 steps for turbo models work perfectly, also CFG of 2.5 to 4.0 works perfectly! |
|
|
|
## Load with 🧨 diffusers |
|
```py |
|
from diffusers import DiffusionPipeline, DPMSolverSinglestepScheduler |
|
import torch |
|
|
|
pipe = DiffusionPipeline.from_pretrained( |
|
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16 |
|
).to("cuda") |
|
#You can use other base models such as `Lykon/dreamshaper-xl-1-0`, `0x4f1f/TurboVisionXL-v3.2` or `SG161222/RealVisXL_V4.0` |
|
|
|
pipe.load_lora_weights( |
|
"mann-e/Mann-E_Turbo", |
|
weight_name="manne_turbo.safetensors", |
|
) |
|
|
|
#This is equivalent to DPM++ SDE Karras, as noted in https://huggingface.co/docs/diffusers/main/en/api/schedulers/overview |
|
pipe.scheduler = DPMSolverSinglestepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True) |
|
|
|
image = pipe( |
|
prompt="a cat in a bustling middle eastern city", |
|
num_inference_steps=8, |
|
guidance_scale=4, |
|
width=768, |
|
height=768, |
|
clip_skip=1 |
|
).images[0] |
|
|
|
image.save("a_cat.png") |
|
``` |
