Instructions to use graizelle/lustmix_anima_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use graizelle/lustmix_anima_v1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("graizelle/lustmix_anima_v1", 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
Graizelle's Lustmix Anima v1
Lustmix Anima | Silk - Glass - Ink
I separated the unet from each Graizelle's Lustmix checkpoint carefully merging each with Anima 1.0 base.
/examples Curated output samples /workflows ComfyUI workflows
Use Qwen text encoder | Qwen VAE same as Anima 1.0 base
Model Characteristics
| Attribute | Rating |
|---|---|
| Prompt Adherence | High |
| Character Consistency | High |
| Realism Bias | Medium-High |
| Anime Style Retention | Medium |
| Skin Detail | High |
| Lighting Detail | High |
| Composition Flexibility | High |
| CFG Sensitivity | Medium |
Recommended Settings
| Setting | Value |
|---|---|
| Sampler | euler, er_sde |
| Scheduler | Simple, Beta57 |
| Steps | 15โ30 |
| CFG | 5โ8 |
| Resolution | 832x1216 |
- Downloads last month
- 109
Model tree for graizelle/lustmix_anima_v1
Base model
nvidia/Cosmos-Predict2-2B-Text2Image Finetuned
circlestone-labs/Anima