mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(image_gen): multi-model FAL support with picker in hermes tools (#11265)

Browse source 
* feat(image_gen): multi-model FAL support with picker in hermes tools

Adds 8 FAL text-to-image models selectable via `hermes tools` →
Image Generation → (FAL.ai | Nous Subscription) → model picker.

Models supported:
- fal-ai/flux-2/klein/9b (new default, <1s, $0.006/MP)
- fal-ai/flux-2-pro (previous default, kept backward-compat upscaling)
- fal-ai/z-image/turbo (Tongyi-MAI, bilingual EN/CN)
- fal-ai/nano-banana (Gemini 2.5 Flash Image)
- fal-ai/gpt-image-1.5 (with quality tier: low/medium/high)
- fal-ai/ideogram/v3 (best typography)
- fal-ai/recraft-v3 (vector, brand styles)
- fal-ai/qwen-image (LLM-based)

Architecture:
- FAL_MODELS catalog declares per-model size family, defaults, supports
  whitelist, and upscale flag. Three size families handled uniformly:
  image_size_preset (flux family), aspect_ratio (nano-banana), and
  gpt_literal (gpt-image-1.5).
- _build_fal_payload() translates unified inputs (prompt + aspect_ratio)
  into model-specific payloads, merges defaults, applies caller overrides,
  wires GPT quality_setting, then filters to the supports whitelist — so
  models never receive rejected keys.
- IMAGEGEN_BACKENDS registry in tools_config prepares for future imagegen
  providers (Replicate, Stability, etc.); each provider entry tags itself
  with imagegen_backend: 'fal' to select the right catalog.
- Upscaler (Clarity) defaults off for new models (preserves <1s value
  prop), on for flux-2-pro (backward-compat). Per-model via FAL_MODELS.

Config:
  image_gen.model           = fal-ai/flux-2/klein/9b  (new)
  image_gen.quality_setting = medium                  (new, GPT only)
  image_gen.use_gateway     = bool                    (existing)

Agent-facing schema unchanged (prompt + aspect_ratio only) — model
choice is a user-level config decision, not an agent-level arg.

Picker uses curses_radiolist (arrow keys, auto numbered-fallback on
non-TTY). Column-aligned: Model / Speed / Strengths / Price.

Docs: image-generation.md rewritten with the model table and picker
walkthrough. tools-reference, tool-gateway, overview updated to drop
the stale "FLUX 2 Pro" wording.

Tests: 42 new in tests/tools/test_image_generation.py covering catalog
integrity, all 3 size families, supports filter, default merging, GPT
quality wiring, model resolution fallback. 8 new in
tests/hermes_cli/test_tools_config.py for picker wiring (registry,
config writes, GPT quality follow-up prompt, corrupt-config repair).

* feat(image_gen): translate managed-gateway 4xx to actionable error

When the Nous Subscription managed FAL proxy rejects a model with 4xx
(likely portal-side allowlist miss or billing gate), surface a clear
message explaining:
  1. The rejected model ID + HTTP status
  2. Two remediation paths: set FAL_KEY for direct access, or
     pick a different model via `hermes tools`

5xx, connection errors, and direct-FAL errors pass through unchanged
(those have different root causes and reasonable native messages).

Motivation: new FAL models added to this release (flux-2-klein-9b,
z-image-turbo, nano-banana, gpt-image-1.5, ideogram-v3, recraft-v3,
qwen-image) are untested against the Nous Portal proxy. If the portal
allowlists model IDs, users on Nous Subscription will hit cryptic
4xx errors without guidance on how to work around it.

Tests: 8 new cases covering status extraction across httpx/fal error
shapes and 4xx-vs-5xx-vs-ConnectionError translation policy.

Docs: brief note in image-generation.md for Nous subscribers.

Operator action (Nous Portal side): verify that fal-queue-gateway
passes through these 7 new FAL model IDs. If the proxy has an
allowlist, add them; otherwise Nous Subscription users will see the
new translated error and fall back to direct FAL.

* feat(image_gen): pin GPT-Image quality to medium (no user choice)

Previously the tools picker asked a follow-up question for GPT-Image
quality tier (low / medium / high) and persisted the answer to
`image_gen.quality_setting`. This created two problems:

1. Nous Portal billing complexity — the 22x cost spread between tiers
   ($0.009 low / $0.20 high) forces the gateway to meter per-tier per
   user, which the portal team can't easily support at launch.
2. User footgun — anyone picking `high` by mistake burns through
   credit ~6x faster than `medium`.

This commit pins quality at medium by baking it into FAL_MODELS
defaults for gpt-image-1.5 and removes all user-facing override paths:

- Removed `_resolve_gpt_quality()` runtime lookup
- Removed `honors_quality_setting` flag on the model entry
- Removed `_configure_gpt_quality_setting()` picker helper
- Removed `_GPT_QUALITY_CHOICES` constant
- Removed the follow-up prompt call in `_configure_imagegen_model()`
- Even if a user manually edits `image_gen.quality_setting` in
  config.yaml, no code path reads it — always sends medium.

Tests:
- Replaced TestGptQualitySetting (6 tests) with TestGptQualityPinnedToMedium
  (5 tests) — proves medium is baked in, config is ignored, flag is
  removed, helper is removed, non-gpt models never get quality.
- Replaced test_picker_with_gpt_image_also_prompts_quality with
  test_picker_with_gpt_image_does_not_prompt_quality — proves only 1
  picker call fires when gpt-image is selected (no quality follow-up).

Docs updated: image-generation.md replaces the quality-tier table
with a short note explaining the pinning decision.

* docs(image_gen): drop stale 'wires GPT quality tier' line from internals section

Caught in a cleanup sweep after pinning quality to medium. The
"How It Works Internally" walkthrough still described the removed
quality-wiring step.
This commit is contained in:
Teknium 2026-04-16 20:19:53 -07:00 • committed by GitHub
parent 0061dca950
commit 01906e99dd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 1245 additions and 468 deletions
Download patch file Download diff file Expand all files Collapse all files

180
website/docs/user-guide/features/image-generation.md
View file

@ -1,18 +1,35 @@
---
title: Image Generation
description: Generate high-quality images using FLUX 2 Pro with automatic upscaling via FAL.ai.
description: Generate images via FAL.ai — 8 models including FLUX 2, GPT-Image, Nano Banana, Ideogram, and more, selectable via `hermes tools`.
sidebar_label: Image Generation
sidebar_position: 6
---
# Image Generation
Hermes Agent can generate images from text prompts using FAL.ai's **FLUX 2 Pro** model with automatic 2x upscaling via the **Clarity Upscaler** for enhanced quality.
Hermes Agent generates images from text prompts via FAL.ai. Eight 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`.
## Supported Models
| Model | Speed | Strengths | Price |
|---|---|---|---|
| `fal-ai/flux-2/klein/9b` *(default)* | <1s | Fast, crisp text | $0.006/MP |
| `fal-ai/flux-2-pro` | ~6s | Studio photorealism | $0.03/MP |
| `fal-ai/z-image/turbo` | ~2s | Bilingual EN/CN, 6B params | $0.005/MP |
| `fal-ai/nano-banana` | ~6s | Gemini 2.5, character consistency | $0.08/image |
| `fal-ai/gpt-image-1.5` | ~15s | Prompt adherence | $0.034/image |
| `fal-ai/ideogram/v3` | ~5s | Best typography | $0.03–0.09/image |
| `fal-ai/recraft-v3` | ~8s | Vector art, brand styles | $0.04/image |
| `fal-ai/qwen-image` | ~12s | LLM-based, complex text | $0.02/MP |
Prices are FAL's pricing at time of writing; check [fal.ai](https://fal.ai/) for current numbers.
## Setup
:::tip Nous Subscribers
If you have a paid [Nous Portal](https://portal.nousresearch.com) subscription, you can use image generation through the **[Tool Gateway](tool-gateway.md)** without a FAL API key. Run `hermes model` or `hermes tools` to enable it.
If you have a paid [Nous Portal](https://portal.nousresearch.com) subscription, you can use image generation through the **[Tool Gateway](tool-gateway.md)** without a FAL API key. Your model selection persists across both paths.
If the managed gateway returns `HTTP 4xx` for a specific model, that model isn't yet proxied on the portal side — the agent will tell you so, with remediation steps (set `FAL_KEY` for direct access, or pick a different model).
:::
### Get a FAL API Key
@ -20,150 +37,117 @@ If you have a paid [Nous Portal](https://portal.nousresearch.com) subscription,
1. Sign up at [fal.ai](https://fal.ai/)
2. Generate an API key from your dashboard
### Configure the Key
### Configure and Pick a Model
Run the tools command:
```bash
# Add to ~/.hermes/.env
FAL_KEY=your-fal-api-key-here
hermes tools
```
### Install the Client Library
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:
```bash
pip install fal-client
```
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
...
```
:::info
The image generation tool is automatically available when `FAL_KEY` is set. No additional toolset configuration is needed.
:::
Your selection is saved to `config.yaml`:
## How It Works
```yaml
image_gen:
model: fal-ai/flux-2/klein/9b
use_gateway: false # true if using Nous Subscription
```
When you ask Hermes to generate an image:
### GPT-Image Quality
1. **Generation** — Your prompt is sent to the FLUX 2 Pro model (`fal-ai/flux-2-pro`)
2. **Upscaling** — The generated image is automatically upscaled 2x using the Clarity Upscaler (`fal-ai/clarity-upscaler`)
3. **Delivery** — The upscaled image URL is returned
If upscaling fails for any reason, the original image is returned as a fallback.
The `fal-ai/gpt-image-1.5` request quality is pinned to `medium` (~$0.034/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 ~22×. If you want a cheaper GPT-Image option, pick a different model; if you want higher quality, use Klein 9B or Imagen-class models.
## Usage
Simply ask Hermes to create an image:
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 portrait of a wise old owl perched on an ancient tree branch
Create a square portrait of a wise old owl — use the typography model
```
```
Make me a futuristic cityscape with flying cars and neon lights
Make me a futuristic cityscape, landscape orientation
```
## Parameters
The `image_generate_tool` accepts these parameters:
| Parameter | Default | Range | Description |
|-----------|---------|-------|-------------|
| `prompt` | *(required)* | — | Text description of the desired image |
| `aspect_ratio` | `"landscape"` | `landscape`, `square`, `portrait` | Image aspect ratio |
| `num_inference_steps` | `50` | 1–100 | Number of denoising steps (more = higher quality, slower) |
| `guidance_scale` | `4.5` | 0.1–20.0 | How closely to follow the prompt |
| `num_images` | `1` | 1–4 | Number of images to generate |
| `output_format` | `"png"` | `png`, `jpeg` | Image file format |
| `seed` | *(random)* | any integer | Random seed for reproducible results |
## Aspect Ratios
The tool uses simplified aspect ratio names that map to FLUX 2 Pro image sizes:
Every model accepts the same three aspect ratios from the agent's perspective. Internally, each model's native size spec is filled in automatically:
| Aspect Ratio | Maps To | Best For |
|-------------|---------|----------|
| `landscape` | `landscape_16_9` | Wallpapers, banners, scenes |
| `square` | `square_hd` | Profile pictures, social media posts |
| `portrait` | `portrait_16_9` | Character art, phone wallpapers |
| Agent input | image_size (flux/z-image/qwen/recraft/ideogram) | aspect_ratio (nano-banana) | image_size (gpt-image) |
|---|---|---|---|
| `landscape` | `landscape_16_9` | `16:9` | `1536x1024` |
| `square` | `square_hd` | `1:1` | `1024x1024` |
| `portrait` | `portrait_16_9` | `9:16` | `1024x1536` |
:::tip
You can also use the raw FLUX 2 Pro size presets directly: `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Custom sizes up to 2048x2048 are also supported.
:::
This translation happens in `_build_fal_payload()` — agent code never has to know about per-model schema differences.
## Automatic Upscaling
Every generated image is automatically upscaled 2x using FAL.ai's Clarity Upscaler with these settings:
Upscaling via FAL's **Clarity Upscaler** is gated per-model:
| Model | Upscale? | Why |
|---|---|---|
| `fal-ai/flux-2-pro` | ✓ | Backward-compat (was the pre-picker default) |
| All others | ✗ | Fast models would lose their sub-second value prop; hi-res models don't need it |
When upscaling runs, it uses these settings:
| Setting | Value |
|---------|-------|
| Upscale Factor | 2x |
|---|---|
| Upscale factor | 2× |
| Creativity | 0.35 |
| Resemblance | 0.6 |
| Guidance Scale | 4 |
| Inference Steps | 18 |
| Positive Prompt | `"masterpiece, best quality, highres"` + your original prompt |
| Negative Prompt | `"(worst quality, low quality, normal quality:2)"` |
| Guidance scale | 4 |
| Inference steps | 18 |
The upscaler enhances detail and resolution while preserving the original composition. If the upscaler fails (network issue, rate limit), the original resolution image is returned automatically.
If upscaling fails (network issue, rate limit), the original image is returned automatically.
## Example Prompts
## How It Works Internally
Here are some effective prompts to try:
```
A candid street photo of a woman with a pink bob and bold eyeliner
```
```
Modern architecture building with glass facade, sunset lighting
```
```
Abstract art with vibrant colors and geometric patterns
```
```
Portrait of a wise old owl perched on ancient tree branch
```
```
Futuristic cityscape with flying cars and neon lights
```
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 if the model's metadata has `upscale: True`.
5. **Delivery** — final image URL returned to the agent, which emits a `MEDIA:<url>` tag that platform adapters convert to native media.
## Debugging
Enable debug logging for image generation:
Enable debug logging:
```bash
export IMAGE_TOOLS_DEBUG=true
```
Debug logs are saved to `./logs/image_tools_debug_<session_id>.json` with details about each generation request, parameters, timing, and any errors.
## Safety Settings
The image generation tool runs with safety checks disabled by default (`safety_tolerance: 5`, the most permissive setting). This is configured at the code level and is not user-adjustable.
Debug logs go to `./logs/image_tools_debug_<session_id>.json` with per-call details (model, parameters, timing, errors).
## Platform Delivery
Generated images are delivered differently depending on the platform:
| Platform | Delivery method |
|----------|----------------|
| **CLI** | Image URL printed as markdown `![description](url)` — click to open in browser |
| **Telegram** | Image sent as a photo message with the prompt as caption |
| **Discord** | Image embedded in a message |
| **Slack** | Image URL in message (Slack unfurls it) |
| **WhatsApp** | Image sent as a media message |
| **Other platforms** | Image URL in plain text |
The agent uses `MEDIA:<url>` syntax in its response, which the platform adapter converts to the appropriate format.
| Platform | Delivery |
|---|---|
| **CLI** | Image URL printed as markdown `![](url)` — click to open |
| **Telegram** | Photo message with the prompt as caption |
| **Discord** | Embedded in a message |
| **Slack** | URL unfurled by Slack |
| **WhatsApp** | Media message |
| **Others** | URL in plain text |
## Limitations
- **Requires FAL API key** — image generation incurs API costs on your FAL.ai account
- **No image editing** — this is text-to-image only, no inpainting or img2img
- **URL-based delivery** — images are returned as temporary FAL.ai URLs, not saved locally. URLs expire after a period (typically hours)
- **Upscaling adds latency** — the automatic 2x upscale step adds processing time
- **Max 4 images per request** — `num_images` is capped at 4
- **Requires FAL credentials** (direct `FAL_KEY` or Nous Subscription)
- **Text-to-image only** — no inpainting, img2img, or editing via this tool
- **Temporary URLs** — FAL returns hosted URLs that expire after hours/days; save locally if needed
- **Per-model constraints** — some models don't support `seed`, `num_inference_steps`, etc. The `supports` filter silently drops unsupported params; this is expected behavior

2
website/docs/user-guide/features/overview.md
View file

@ -30,7 +30,7 @@ Hermes Agent includes a rich set of capabilities that extend far beyond basic ch
- **[Voice Mode](voice-mode.md)** — Full voice interaction across CLI and messaging platforms. Talk to the agent using your microphone, hear spoken replies, and have live voice conversations in Discord voice channels.
- **[Browser Automation](browser.md)** — Full browser automation with multiple backends: Browserbase cloud, Browser Use cloud, local Chrome via CDP, or local Chromium. Navigate websites, fill forms, and extract information.
- **[Vision & Image Paste](vision.md)** — Multimodal vision support. Paste images from your clipboard into the CLI and ask the agent to analyze, describe, or work with them using any vision-capable model.
- **[Image Generation](image-generation.md)** — Generate images from text prompts using FAL.ai's FLUX 2 Pro model with automatic 2x upscaling via the Clarity Upscaler.
- **[Image Generation](image-generation.md)** — Generate images from text prompts using FAL.ai. Eight models supported (FLUX 2 Klein/Pro, GPT-Image 1.5, Nano Banana, Ideogram V3, Recraft V3, Qwen, Z-Image Turbo); pick one via `hermes tools`.
- **[Voice & TTS](tts.md)** — Text-to-speech output and voice message transcription across all messaging platforms, with five provider options: Edge TTS (free), ElevenLabs, OpenAI TTS, MiniMax, and NeuTTS.
## Integrations

2
website/docs/user-guide/features/tool-gateway.md
View file

@ -18,7 +18,7 @@ The **Tool Gateway** lets paid [Nous Portal](https://portal.nousresearch.com) su
| Tool | What It Does | Direct Alternative |
|------|--------------|--------------------|
| **Web search & extract** | Search the web and extract page content via Firecrawl | `FIRECRAWL_API_KEY`, `EXA_API_KEY`, `PARALLEL_API_KEY`, `TAVILY_API_KEY` |
| **Image generation** | Generate images via FAL (FLUX 2 Pro + upscaling) | `FAL_KEY` |
| **Image generation** | Generate images via FAL (8 models: FLUX 2 Klein/Pro, GPT-Image, Nano Banana, Ideogram, Recraft, Qwen, Z-Image) | `FAL_KEY` |
| **Text-to-speech** | Convert text to speech via OpenAI TTS | `VOICE_TOOLS_OPENAI_KEY`, `ELEVENLABS_API_KEY` |
| **Browser automation** | Control cloud browsers via Browser Use | `BROWSER_USE_API_KEY`, `BROWSERBASE_API_KEY` |