توليد الصور

Hermes Agent generates images from text prompts via FAL.ai. Eleven models are supported out of the box, each with different speed, quality, and cost tradeoffs. The active model is user-configurable via hermes tools and persists in config.yaml.

Prices are FAL's pricing at time of writing; check fal.ai ↗ for current numbers.

Get a FAL API Key

1. Sign up at fal.ai ↗
2. Generate an API key from your dashboard

Configure and Pick a Model

Run the tools command:

hermes tools

Navigate to 🎨 Image Generation, pick your backend (Nous Subscription or FAL.ai), then the picker shows all supported models in a column-aligned table — arrow keys to navigate, Enter to select:

  Model                          Speed    Strengths                    Price
  fal-ai/flux-2/klein/9b         <1s      Fast, crisp text             $0.006/MP   ← currently in use
  fal-ai/flux-2-pro              ~6s      Studio photorealism          $0.03/MP
  fal-ai/z-image/turbo           ~2s      Bilingual EN/CN, 6B          $0.005/MP
  ...

Your selection is saved to config.yaml:

image_gen:
  model: fal-ai/flux-2/klein/9b
  use_gateway: false            # true if using Nous Subscription
  max_parallel_requests: 4      # concurrent images in one tool-call batch

max_parallel_requests defaults to 4. Hermes clamps it to at least one and to the global tool-worker limit, so image providers receive bounded parallel requests without allowing an image batch to bypass the agent's concurrency cap.

GPT-Image Quality

The fal-ai/gpt-image-1.5 and fal-ai/gpt-image-2 request quality is pinned to medium (~$0.034–$0.06/image at 1024×1024). We don't expose the low / high tiers as a user-facing option so that Nous Portal billing stays predictable across all users — the cost spread between tiers is 3–22×. If you want a cheaper option, pick Klein 9B or Z-Image Turbo; if you want higher quality, use Nano Banana Pro or Recraft V4 Pro.

The agent-facing schema is intentionally minimal — the model picks up whatever you've configured:

Generate an image of a serene mountain landscape with cherry blossoms

Create a square portrait of a wise old owl — use the typography model

Make me a futuristic cityscape, landscape orientation

The same image_generate tool also edits existing images when the active model supports it — pass a source image and the backend routes to its editing endpoint automatically (mirrors how video_generate handles image-to-video). Omit the source image and it's plain text-to-image.

Take this photo and make it a rainy Tokyo street at night → <image>

Blend these two product shots into one hero image → <image1> <image2>

Two inputs drive the edit:

• image_url — the primary source image to edit/transform (public URL or local path).
• reference_image_urls — additional style/composition references (capped per-model).

Which backends support editing

FAL models with an editing endpoint: flux-2/klein/9b, flux-2-pro, nano-banana-pro, gpt-image-1.5, gpt-image-2, ideogram/v3, and qwen-image. Pure text-to-image FAL models (z-image/turbo, recraft, krea/*) reject image inputs with a clear error pointing you at an edit-capable model.

The active model's editing capability is surfaced in the tool description at runtime, so the agent knows whether image_url will be honored before it calls the tool.

Every model accepts the same three aspect ratios from the agent's perspective. Internally, each model's native size spec is filled in automatically:

GPT Image 2 maps to 4:3 presets rather than 16:9 because its minimum pixel count is 655,360 — the landscape_16_9 preset (1024×576 = 589,824) would be rejected.

This translation happens in _build_fal_payload() — agent code never has to know about per-model schema differences.

Opt-in only

No model upscales by default. Modern image models emit their best quality natively, and the available upscalers are creative enhancers (diffusion passes) that can subtly redraw content — degrading rendered text, faces, and fine detail. Upscaling only runs when the agent explicitly requests it.

The upscale parameter (per-call opt-in)

• upscale: true — chain a high-resolution pass after generation:

• upscale: false / omitted — native resolution (the default)

video_generate also accepts upscale: true on the FAL backend, chaining ByteDance's SeedVR2 video upscaler (2×, $0.001/MP of output video) after generation.

When the FAL image pass runs, it uses these settings:

If upscaling fails (network issue, rate limit), the original image is returned automatically. The response reports upscaled: true/false so the agent knows which resolution it got.

1. Model resolution — _resolve_fal_model() reads image_gen.model from config.yaml, falls back to the FAL_IMAGE_MODEL env var, then to fal-ai/flux-2/klein/9b.
2. Payload building — _build_fal_payload() translates your aspect_ratio into the model's native format (preset enum, aspect-ratio enum, or GPT literal), merges the model's default params, applies any caller overrides, then filters to the model's supports whitelist so unsupported keys are never sent.
3. Submission — _submit_fal_request() routes via direct FAL credentials or the managed Nous gateway.
4. Upscaling — runs only when the agent passed upscale: true; every model's catalog default is off.
5. Delivery — final image URL returned to the agent, which emits a MEDIA:<url> tag that platform adapters convert to native media.

Enable debug logging:

export IMAGE_TOOLS_DEBUG=true

Debug logs go to ./logs/image_tools_debug_<session_id>.json with per-call details (model, parameters, timing, errors).

• Requires credentials for the active backend (FAL FAL_KEY / Nous Subscription, OPENAI_API_KEY, xAI OAuth, KREA_API_KEY)
• Editing is model-dependent — image-to-image works only on edit-capable models (see the table above); text-to-image-only models reject image inputs with a clear error
• Temporary URLs — backends return hosted URLs that expire after hours/days; Hermes materializes them to the local cache so delivery still works after expiry
• Per-model constraints — some models don't support seed, num_inference_steps, etc. The supports / edit_supports filter silently drops unsupported params; this is expected behavior