custom-model-traininglisted

Trains a custom Ideogram model on a folder of reference images, then generates a new image with that trained model to prove it works — a real end-to-end pipeline (create_dataset, upload_dataset_assets, train_model, poll get_model, generate_image with custom_model_uri), not just an explanation of how training works. Use whenever the user wants to "train a custom model," "fine-tune" on their own images, get "consistent" output of a specific character, product, or brand across many future generations, lock in a look so it doesn't drift between generations, or turns a set of reference images (including a previously generated brand-identity-sheet or character-model-sheet) into a reusable model. Also trigger this when the user asks what a `custom_model_uri` is or how to get one — that URI only exists after running this pipeline. Distinct from `brand-identity-sheet` and `character-model-sheet`, which produce the single locked reference image in the first place; this skill is the next step, turning that locked image
devkindhq/ideogram-ai-toolkit · ★ 2 · AI & Automation · score 70

Install: claude install-skill devkindhq/ideogram-ai-toolkit

# Custom Model Training Ideogram lets you train a custom model on your own reference images, then generate new images that stay consistent with those references via a `custom_model_uri` passed to `generate_image`. This is the skill that closes the loop other skills in this toolkit start: `brand-identity-sheet` locks a brand system into one image; `character-model-sheet` locks a character into one multi-panel turnaround. Once that reference exists, this skill turns it (plus any other reference images) into a model that generates on-brand or on-character assets indefinitely, instead of re-describing the same look in every future prompt and hoping it stays consistent. Always run the pipeline — create the dataset, upload the images, kick off training, poll until it's ready, and generate a proof image with the trained model — rather than stopping after `train_model` and telling the user to check back later. The prompt-only version of this skill would just be a description of the Ideogram API; the value is in actually running it, watching training through to completion, and coming back with a generated image that demonstrates the model works. ## Before you start: read the honest facts Read `references/dataset-requirements.md` before running the pipeline. It splits what's actually confirmed about these tools (from direct inspection of their schemas) from what's genuinely unknown (minimum image count, training duration, the exact "ready" status value). Don't invent numbers for th