Instructions to use Gourieff/protogen_v2.2_reconverted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Gourieff/protogen_v2.2_reconverted with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Gourieff/protogen_v2.2_reconverted", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
metadata
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
Protogen v2.2 --reconverted
Works fine without errors with NMKD (tested with 1.7+) and other GUI/webUI
You can download CKPT model here
This is a mix by darkstorm2150 of such models as:
- f22_v1.ckpt
- elldrethSLucidMix_V10.cpkt
- hassanBlendAllVersio_hassanBlend14.ckpt
- seek_art_mega_v1.ckpt
- modelshoot-1.0.ckpt
To center the image on intended subject use the token:
modelshoot style
Camera Prompt Commands by MC Mic:
(from_above:1.3), (from_below:1.3),(from_side:1.3),(from_behind:1.3),
Movement Control:
(hand_on_hip:1.2), (sitting:1.2),
Sample result:
