Image

Bonsai Image Generator

Type a prompt or upload a photo and download a PNG — compact 1-bit Bonsai Image text-to-image and editing on devices you connect.

Bonsai Image by Prism ML; FLUX.2 klein by Black Forest Labs; Qwen3 by Alibaba Cloud

Model licenses

Prism ML Bonsai Image binary DiT · Apache-2.0

Retain complete Apache-2.0 licence, upstream copyright and NOTICE texts; prominently identify modified files. Patent termination and trademark limitations apply. Prism ML requests public attribution, preserved here and in the catalog.

Distributed license

Notice

FLUX.2 klein VAE and shared pipeline/tokenizer derivatives · Apache-2.0

Retain complete Apache-2.0 licence, upstream copyright and NOTICE texts; prominently identify modified files. Patent termination and trademark limitations apply.

Qwen3-4B text encoder distributed by FLUX.2 klein · Apache-2.0

FreeOnlineUnlimitedBonsai Image by Prism ML; FLUX.2 klein by Black Forest Labs; Qwen3 by Alibaba Cl API access

API reference

Submit via REST

Use your personal API key (msk_…) to create jobs for this workload from your own tools. Jobs started this way run on the same devices you connected on Your Devices — at least one has to be online.

Hide API details
POSThttps://cp.meshlabs.cloud/v1/organizations/jobs

Authenticate with X-Organization-Api-Key: msk_your_personal_api_key. The header name matches org keys; personal keys use the same endpoint.

Input files:Call POST https://cp.meshlabs.cloud/v1/organizations/job-inputs/presign with the same API key, upload your file to the returned upload_url, then pass download_url in job_spec (for example as input_image_url).

Request body

{
  "workload_type": "bonsai-image-binary-4b",
  "job_spec": {
    "prompt": "A photorealistic lighthouse at dusk",
    "width": 1024,
    "height": 1024,
    "strength": 0.8,
    "steps": 4,
    "shift": 3,
    "compression_method": "fp16"
  }
}

job_spec fields

FieldRequiredDefaultDescription
promptYes—Text description of the image, or the edit instruction when an input image is set.
input_image_urlNo—Optional input image for image editing (img2img). When set, the image is VAE-encoded and mixed with noise by 'strength'; the prompt describes the desired edit.
widthNo1024Output width in pixels (multiple of 16).
heightNo1024Output height in pixels (multiple of 16).
strengthNo0.8img2img noise fraction: 0.3 = light touch-up, 0.8 = heavy edit, 1.0 = ignore the input image. Only used with input_image_url.
stepsNo4Denoising steps (Bonsai Image is distilled to 4).
seedNo—Random seed for reproducible generation.
shiftNo3Flow-match schedule shift. The model is designed for 3.0.
compression_methodNofp16Codec for FP32 inter-node DiT activation handoffs.

cURL

curl -X POST https://cp.meshlabs.cloud/v1/organizations/jobs \
  -H "X-Organization-Api-Key: msk_your_personal_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "workload_type": "bonsai-image-binary-4b",
  "job_spec": {
    "prompt": "A photorealistic lighthouse at dusk",
    "width": 1024,
    "height": 1024,
    "strength": 0.8,
    "steps": 4,
    "shift": 3,
    "compression_method": "fp16"
  }
}'
GEThttps://cp.meshlabs.cloud/v1/organizations/jobs/{job_id}

Poll with the same API key until status is terminal (COMPLETED, FAILED, CANCELED, or MODERATION_BLOCKED). When content moderation is enabled, jobs may start in MODERATION_PENDING before entering the compute queue. Completed jobs include presigned download_url values on each output.

Create response

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "bonsai-image-binary-4b",
  "status": "PENDING",
  "job_spec_json": {
    "prompt": "A photorealistic lighthouse at dusk",
    "width": 1024,
    "height": 1024,
    "strength": 0.8,
    "steps": 4,
    "shift": 3,
    "compression_method": "fp16"
  },
  "work_units": [],
  "outputs": [],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "2026-06-08T12:00:00Z"
}

Completed response

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "bonsai-image-binary-4b",
  "status": "COMPLETED",
  "job_spec_json": {
    "prompt": "A photorealistic lighthouse at dusk",
    "width": 1024,
    "height": 1024,
    "strength": 0.8,
    "steps": 4,
    "shift": 3,
    "compression_method": "fp16"
  },
  "work_units": [
    {
      "id": "…",
      "index": 0,
      "status": "COMPLETED"
    }
  ],
  "outputs": [
    {
      "id": "…",
      "output_type": "<output type>",
      "filename": "<output filename>",
      "size_bytes": 524288,
      "download_url": "<presigned output download URL>"
    }
  ],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "<completion timestamp>"
}

Type a text prompt or upload a photo and describe the edit, then download a PNG. Bonsai Image Generator is a free online AI image generator and image editor: Prism ML's compact 1-bit FLUX.2 Klein 4B pack turns natural-language descriptions into pictures in four steps, or lightly edits an uploaded photo, running unlimited on the computers you connect to MESH. Native size is 1024×1024; 512×512 is a faster preview. Negative prompts are not needed. Prefer the ternary listing when you want higher visual fidelity on the same Klein architecture.