anima · hyperrealism studio

Auto-upscale (Upscayl)

Spawn

Start

End

Loop

Upscale

Animate

Drive

Fav

Bin

Photograph Hyperreal 4K

1

1 · Realism scaffold

2 · Controls

3 · Intent

Video Production

Start frame

Send an image here from the Studio → "Set as start frame"

End frame (optional)

optional end frame

8s

Loop

Video pipeline

Upscayl — ad-hoc upscale

Drop or pick an image; it is upscaled with the Upscayl engine (Real-ESRGAN) on the server and returned for download.

Click or drop an image to upscale

Recycle bin

Soft-deleted images. Restore them to the pipeline or delete permanently.

Nothing here.

Agents — generate images via the n8n webhook

One HTTP POST returns a hosted image URL. Give agents this endpoint and the recipe presets below. Full reference lives in the skill on GitHub.

↗ Open the anima-n8n-webhook skill on GitHub

Endpoint

POST https://n8n.divergence.systems/webhook/anima/generate
Content-Type: application/json

Request body

{
  "prompt": "who + doing what + where — one concrete sentence, no style words",
  "model": "nano-banana-pro",
  "aspect_ratio": "3:2",
  "resolution": "2K",
  "controls": "optional: lens + light + mood (use a recipe below)"
}

aspect_ratio: 1:1 · 3:2 · 2:3 · 16:9 · 9:16. resolution: 1K · 2K. The realism floor (photoreal scaffold + anti-AI-tell negatives) is added automatically, so do not write "photorealistic" or "4K" yourself. Provider defaults to Kie; do not use OpenAI.

Image models (pass as model)

nano-banana-proNano Banana Pro — default · WOW. Best faces/skin; ~40-54s; up to 8 image_input refs. seedream/4.5-text-to-imageSeedream 4.5 · WOW. Fast (~17s), cheap; resolution 4K = high quality. Best for volume. flux-2/pro-text-to-imageFLUX.2 Pro · WOW. Fast (~21s), optical realism, max 2K. qwen/image-editQwen Image Edit · WOW. Needs a source image (image_url / image_input). gpt-image-2-text-to-imageGPT Image 2 · slow (~76-180s). ⚠ Do NOT use via the webhook — exceeds the ~60s cap. Studio only. nano-banana-2-liteNano Banana 2 Lite · Lite. Fast, accepts refs. ideogram/v3-text-to-imageIdeogram v3 · Lite. nsfw_checker forced off. qwen/text-to-imageQwen Image · Lite. Fast general text-to-image.

Response

{ "ok": true, "url": "https://res.cloudinary.com/.../anima/xxxx.jpg", "engine": "Kie" }

Recipe presets (aspect_ratio + controls)

Editorial consult · 3:250mm f/2.0, soft window light, editorial grade, modern office. Consultations, team, advisory. Golden-hour lifestyle · 2:3Golden-hour backlight, 35mm, warm cinematic, aspirational. People, families, heroes. Document flat-lay · 1:1Overhead flat lay, soft studio softbox, premium product. Documents, passports, cards. Landmark wide · 3:224mm, blue hour, HDR travel photography. City and landmark heroes, banners. Human trust · 1:185mm f/1.8, warm close-up, trust-and-care. Handshakes, "we care" blocks.

Copy-paste example

curl -s -X POST https://n8n.divergence.systems/webhook/anima/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A friendly migration consultant advising a relaxed client across a desk, Thailand visa documents on the table","model":"nano-banana-pro","aspect_ratio":"3:2","resolution":"2K"}'

Prompt library

Save your best prompts to reuse. "New prompt" grabs whatever is in the Studio composer; "Use in Studio" loads one back in.

Logs

Recent generation events. Failures include the per-lane error so you can see exactly what went wrong (and which engine flaked).

Upscayl — ad-hoc upscale

Recycle bin

Agents — generate images via the n8n webhook

Prompt library

Logs

Pricing reference

Image