Instructions to use SeeSee21/chroma-Semi-Anime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SeeSee21/chroma-Semi-Anime with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lodestones/Chroma", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("SeeSee21/chroma-Semi-Anime") 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
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("lodestones/Chroma", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("SeeSee21/chroma-Semi-Anime")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]A style LoRA for lodestones/Chroma that pushes generations toward a semi-anime look with photorealistic detail, while keeping Chroma's strong composition.
chroma-Anime.safetensors, set the strength to 0.8 (clip skip 1) and start your prompt with the trigger word hanime.
β¨ At a glance
| Property | Details |
|---|---|
| π§© Type | Style LoRA (version V1, the only version on Civitai) |
| ποΈ Base model | lodestones/Chroma |
| π File | chroma-Anime.safetensors (13.44 MB) β ComfyUI/models/loras/ |
| ποΈ Strength | 0.8 recommended (0.6 β 1.0) |
| π Trigger word | hanime |
| π§ͺ Training | 10 epochs Β· 575 steps Β· 371 MB of training images Β· uploaded Sep 26, 2025 |
πΌοΈ Preview gallery
All images were posted to the V1 version on Civitai.
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
π About this LoRA
Chroma Semi-Anime brings semi-anime characters to life with photorealistic details. It excels at cute and fantasy-themed anime girls with diverse body types, outfits and accessories.
Whether you want casual everyday fashion, expressive poses or fantasy and magical settings, it delivers high-quality semi-anime results with careful attention to lighting, perspective and detail.
π Key features
- π Fully clothed designs and dynamic outfits included
- ποΈ Diverse body types: curvy, slim, petite, athletic, goddess-like
- πΈ Multiple camera angles and poses for rich compositions
- π¨ Great for character art and concept illustrations
- π Photorealistic semi-anime rendering with expressive visuals
ποΈ Recommended settings
| Setting | Value |
|---|---|
| Strength | 0.8 (start between 0.6 and 1.0) |
| Clip skip | 1 |
| Trigger word | hanime (put it at the start of the prompt) |
| Recommended for | Fantasy art, cute anime girls |
| Prompt style | Natural language works well on Chroma: describe subject, style and lighting clearly |
π‘ Tip: experiment with different poses, outfits and fantasy scenarios. Combine the LoRA with your favorite base models to get unique semi-anime artwork.
π Suggested use in ComfyUI
- Load a Chroma checkpoint or workflow.
- Add a LoRA loader and select
chroma-Anime.safetensors. - Start at a strength of about 0.8 (range 0.6 β 1.0) and begin the prompt with
hanime. - Describe the subject, style and lighting in natural language.
Example negative prompt (SFW default):
nsfw, nude, explicit, worst quality, bad anatomy, watermark, jpeg artifact
π§© Workflow
The Civitai page of this LoRA publishes no workflow. Use it with your usual Chroma workflow and a LoRA loader.
π Content notice
The original Civitai description also covers adult content, which is not reproduced here. The LoRA can produce stylized adult-looking characters. Please use it responsibly and only if you are 18 or older.
π License & attribution
- LoRA training: SeeSee (Hugging Face:
SeeSee21, Civitai:SeeSeeLP). - Base model: lodestones/Chroma, Apache-2.0.
- The weights in this repository are released under Apache-2.0, consistent with the base model.
π§ More from SeeSee β all models
π§© Checkpoints & AIO
| Model | Hugging Face | Civitai |
|---|---|---|
| AniSee | SeeSee21/AniSee | Model Β· Workflows |
| Z-Anime | SeeSee21/Z-Anime | Model |
| Z-Image-Turbo-AIO | SeeSee21/Z-Image-Turbo-AIO | Model Β· Workflow |
| ERNIE-AIO | SeeSee21/ERNIE-AIO | Model Β· Workflow |
| Chroma-Anime-AIO | SeeSee21/Chroma-Anime-AIO | Model Β· Workflow |
| FLUX.2-klein-4B-AIO | SeeSee21/FLUX.2-klein-4B-AIO | Model Β· Workflow |
| QWEN-Anime | SeeSee21/QWEN-Anime | Model Β· Workflow |
| SeeMoss-Genesis | SeeSee21/SeeMoss-Genesis | Model Β· Workflow |
| See-Krea2 | SeeSee21/Krea-2-See-Krea2-Genesis | Model Β· Workflow |
π LoRAs
| Model | Hugging Face | Civitai |
|---|---|---|
| Illustrious Anime Collection | SeeSee21/Illustrious-Anime-Collection | Model |
| Chroma Semi-Anime | SeeSee21/chroma-Semi-Anime | Model |
| Kitsune Furry Girl | SeeSee21/Kitsune-Furry-Girl-Z-Image | Model |
| Ayase Momo (Dandadan) | SeeSee21/Ayase-Momo-Z-Image | Model |
π§© Checkpoints & AIO Β· π LoRAs Β· π Civitai Β· βΆοΈ YouTube
Made with β€οΈ by SeeSee
- Downloads last month
- 12
Model tree for SeeSee21/chroma-Semi-Anime
Base model
lodestones/Chroma







