Instructions to use mann-e/mann-e_4_rev-1-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mann-e/mann-e_4_rev-1-3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mann-e/mann-e_4_rev-1-3", 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 Settings
- Draw Things
- DiffusionBee
| license: mit | |
| tags: | |
| - text-to-image | |
|  | |
| # Mann-E 4 (revision 1.3) | |
| _Mann-E_ (which is read Mani or in Persian مانی) is a state-of-the-art AI art generator made by [Muhammadreza Haghiri](https://haghiri75.com/en) as a part of [Open Cognitives](https://opencognitives.com) projects. The goal of this project was to bring a Free/Libre and Open Source (FLOSS for short) equivalent of [Midjourney](https://midjourney.com). This model is based on [Stable Diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) and the data gathered from the internet and also has its own unique text encoder. | |
| ## Colab Access | |
| Clink on [this link](https://colab.research.google.com/github/prp-e/mann-e/blob/main/Mann_E.ipynb) to accesss our web user interface through colab. | |
| ## Samples (with prompts) | |
|  | |
| __Prompt__: | |
| ``` | |
| gtav style, a young beautiful woman with blonde hair wearing sunglasses, retrowave, art by midjourney | |
| ``` | |
| __Negative Prompt__: | |
| ``` | |
| low quality, blurry, hand, hands, arms, ribs | |
| ``` | |
| Sampler _Euler a_ and CFG Scale 10. | |
|  | |
| __Prompt__: | |
| ``` | |
| gtav style, a young beautiful woman with blonde hair wearing sunglasses, retrowave, art by midjourney | |
| ``` | |
| __Negative Prompt__: | |
| ``` | |
| low quality, blurry, hand, hands, arms, ribs | |
| ``` | |
| Sampler _DPM++SDE Kerras_ and CFG Scale 10. | |
|  | |
| __Prompt__: | |
| ``` | |
| valorant style, a young beautiful woman with blonde hair wearing sunglasses, retrowave, art by midjourney | |
| ``` | |
| __Negative Prompt__: | |
| ``` | |
| low quality, blurry, hand, hands, arms, ribs | |
| ``` | |
| Sampler _DPM++SDE Kerras_ and CFG Scale 10. | |
|  | |
| __Prompt__: | |
| ``` | |
| arcane style, a young man wearing leather jacket, art by midjourney | |
| ``` | |
| __Negative Prompt__: | |
| ``` | |
| low quality, blurry, hand, hands, arms, ribs | |
| ``` | |
| Sampler _DPM++SDE Kerras_ and CFG Scale 10. | |
| ## More advanced prompts (better and more coherent results) | |
|  | |
| __Prompt__: | |
| ``` | |
| ultra realistic illustration of a young beautiful woman with blonde curly hair, intricate details, elegant, sharp focus, smooth edges, trending on artstation, digital painting, art by artgerm, greg rutkowski, alphonse mucha, albert lynch and midjourney | |
| ``` | |
| __Negative Prompt__: | |
| ``` | |
| low quality, blurry, hand, hands, arms, ribs | |
| ``` | |
| Sampler _DPM++SDE Kerras_ and CFG Scale 10. | |
|  | |
| __Prompt__: | |
| ``` | |
| a house in a stunningly beautiful landscape, reflection in the water, blue hour, concept art, digital painting, art by midjourney | |
| ``` | |
| __Negative Prompt__: | |
| ``` | |
| low quality, blurry, cartoon | |
| ``` | |
| Sampler _DPM++SDE Kerras_ and CFG Scale 10. | |