recommend_training

Pick a Scenario training base architecture: image LoRA family + variant, or voice clone, from a user training intent.

When to use

Call this tool when the user asks "which model should I train" / "what LoRA base fits my dataset" / "voice clone for X". It returns the exact type string to pass to manage_models create. For picking models that generate outputs, use recommend instead.

Decision tree

The picker filters by dataset shape, scores by style + subject, then picks a variant inside the winning family by priority.

Image families

Family	Kind	Best for	Status
Flux 2	standard	New projects training a single-image LoRA — characters, products, environments, or distinctive styles.	stable
Flux 2 Edit	edit	When your dataset is image pairs with text instructions describing the change.	stable
Qwen Image	standard	High-volume use cases where budget matters and you want strong prompt adherence.	stable
Qwen Edit	edit	Edit recipes that should keep the surrounding context intact.	stable
Z-Image	standard	Stylized work — character art, illustration, concept art — or anywhere the highest training fidelity matters.	stable
Flux 1 Dev	standard	Existing projects with Flux 1 LoRAs already in production. New projects should use Flux 2.	legacy
Flux Kontext	edit	Existing edit recipes already using Flux Kontext. Consider Flux 2 Edit or Qwen Edit for new projects.	legacy

Voice options

Instant Voice Cloning (IVC) (stable) — Quick voice clone from a short audio sample. Ready in seconds.
Professional Voice Clone (soon) — High-fidelity clone trained on longer, cleaner audio — better expressiveness and realism.

Required inputs

At minimum, pass prompt describing the training goal — the LLM extracts everything else. Hosts that already know the modality + dataset shape can pass them as structured params and skip LLM 1.

Output shape

{
  family: "Flux 2",
  recommended: {
    type: "flux.2-dev-lora",
    label: "Dev (32B)",
    why: "..."
  },
  alternatives: [
    { type, when_better, tradeoff }
  ],
  dataset_requirements: {
    shape: "single_images",
    recommended_size: "5-15 images",
    max_size: 50
  },
  family_notes?: string,
  resolution_notes: string,
  _degraded?: "llm_unavailable" | "llm_timeout"
}

Worked examples

Image — character LoRA

Prompt: "I have 30 photos of my dog. Train a model."

family: Flux 2
recommended: flux.2-dev-lora
dataset: 5–15 single images, max 50

Voice — quick clone

Prompt: "15-second voice memo, want a quick clone."

family: Instant Voice Cloning (IVC)
recommended: voice-clone-ivc
dataset: short audio sample, <30s

Reference

Public training docs: docs.scenario.com/get-started/training/training-models