Instructions to use BlackHat404/DefacationAnima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BlackHat404/DefacationAnima with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("circlestone-labs/Anima", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("BlackHat404/DefacationAnima") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| - not-for-all-audiences | |
| widget: | |
| - output: | |
| url: images/censor1.png | |
| text: '-' | |
| - output: | |
| url: images/censor2.png | |
| text: '-' | |
| - output: | |
| url: images/censor3.png | |
| text: '-' | |
| base_model: circlestone-labs/Anima | |
| instance_prompt: defecating, poop_pile, laying_cable, thick_turds | |
| license: openrail | |
| # Defecation(Anima) | |
| <Gallery /> | |
| ## Model description | |
| CONTENT WARNING: SCAT | |
| CivitAI account in case you didn't come from there.(https://civitai.com/user/DarkModeOP) | |
| Ko-Fi if you are really generous.(I don't need the money, I have a comfy life.) https://ko-fi.com/darkmodeop | |
| Here is a LoRA model that is way too spicy for CivitAI. | |
| Lensdump for non-censored images. https://lensdump.com/a/X4Zp0 | |
| Hello again, it's been a long while because for once I seem to be close to bleeding edge of a new model release. | |
| This time around I've added a bit more control over the output(pun intended) so now you should be able to prompt for piles(poop_pile) or logs that tend not to pile up(laying_cable). Adding thick_turds to the prompt should result and thicker output but sometimes it doesn't work super well. | |
| Full Generation parameters for purple streaked hair example image. | |
| masterpiece, best_quality, absurdres, amazing_quality, long_hair, sitting, office_lady, office_chair, blazer, skirt_lift, office, pale_skin, bags_under_eyes, medium_breasts, blush, sigh, steam, black_hair, purple single_hair_streak, futanari, penis, testicles, from_behind, anus, <lora:DefecationAnimaComboV1:0.99> defecating, laying_cable | |
| Negative prompt: bad_quality, worst_quality, worst_detail, sketch, censored, watermark, signature, artist_name, patreon_username, patreon_logo, worst_aesthetic, low_quality, lowres | |
| Steps: 25, Sampler: DPM++ 2M, Schedule type: Beta, CFG scale: 4, Shift: 3, Seed: 3843698293, Size: 960x1728, Model hash: 4bf3ec72ec, Model: perfectrsbmixAnimaAIO_epsilon, Module 1: qwen_image_vae, Module 2: anima_qwen_3_06b_base, Clip skip: 2, RNG: CPU, Lora hashes: "DefecationAnimaComboV1: 6cf4d4fbc5a2", Beta schedule alpha: 0.6, Beta schedule beta: 0.6, Version: neo | |
| ## Trigger words | |
| You should use `defecating` to trigger the image generation. | |
| You should use `poop_pile` to trigger the image generation. | |
| You should use `laying_cable` to trigger the image generation. | |
| You should use `thick_turds` to trigger the image generation. | |
| ## Download model | |
| [Download](/BlackHat404/DefacationAnima/tree/main) them in the Files & versions tab. | |