Anima Text To Image LoRA API Documentation

Anima Text To Image LoRA API Documentation

Playground

Anima with LoRA support runs custom character and style LoRAs on CircleStone Labs’ 2B anime model, generating personalized anime illustrations natively at 1K to 1.5K resolution, with both text-to-image and image-to-image support. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Anima LoRA is a fast, aesthetic-first image generation model for both text-to-image and image-to-image workflows. It supports native 1k and 1.5k output, and adds on-the-fly LoRA loading so you can apply up to 3 LoRAs in a single request for more targeted style and subject control.

Why Choose This?

• Native high-resolution generation
  Generate images at 1k or 1.5k resolution without relying on a separate upscaling pass.

• Fast Turbo workflow
  The Turbo checkpoint is optimized for fast generation, making it suitable for quick prompt iteration and production workflows.

• LoRA support
  Load up to 3 LoRAs per request, each with its own scale, for stronger style, subject, or concept control.

• Text-to-image and image-to-image
  Generate from a text prompt alone, or provide an image input for guided restyling and variation.

• Flexible image-to-image strength
  Use strength to control how strongly the model follows or repaints the source image.

• Wide aspect ratio support
  Supports square, portrait, landscape, tall, wide, and cinematic aspect ratio presets.

Parameters

How to Use

1. Write your prompt — Describe the subject, composition, lighting, style, and visual details.
2. Choose resolution — Use 1k for faster iteration or 1.5k for higher-resolution output.
3. Select aspect ratio — Pick the layout that matches your target format.
4. Add image optional — Provide an image when using image-to-image generation.
5. Adjust strength optional — Lower values preserve more of the source image, while higher values allow stronger repainting.
6. Add LoRAs optional — Provide up to 3 LoRAs, each with its own path and scale.
7. Set seed optional — Use a fixed seed for more reproducible results.
8. Submit — Generate the final image.

Pricing

Pricing is based on selected resolution.

Best Use Cases

• LoRA-guided image generation — Apply custom styles, subjects, or concept tuning with one or more LoRAs.
• Text-to-image creation — Generate polished images from natural-language prompts.
• Image variation and restyling — Use a source image with prompt control for creative reinterpretation.
• Marketing and creative assets — Generate campaign visuals, product concepts, and branded creative content.
• Concept exploration — Test different looks, styles, and directions quickly with Turbo generation.
• Higher-resolution final assets — Use 1.5k when you need more detailed final output.

Pro Tips

• Use detailed prompts with subject, composition, lighting, mood, and style direction.
• Use 1k for faster testing and 1.5k for final-quality output.
• For image-to-image, strength around 0.4–0.6 usually preserves more composition, while 0.7–0.9 allows more aggressive repainting.
• Start LoRA scale around 0.8–1.0, then lower it if the LoRA effect becomes too dominant.
• Use fewer LoRAs when you need tighter control, and combine multiple LoRAs only when their effects are compatible.
• Set a fixed seed when comparing prompt or LoRA changes.

Related Models

• Anima Text-to-Image — The same model without LoRA loading.

Reference

• How to train your LoRA?
• How to use your LoRA?

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "strength": 0.8
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/anima/text-to-image-lora" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters