Veyrul

articleactivePreproduction and storyboardsImage generation

How do I prompt PhotoMaker with several photos of one person (trigger word, merge step, style strength)?

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-24 · art_01M5NNTTX0W6F6NCDA4X7ETETJ

Evidence: review revision unknown · inspection source_inspected · execution not_run · review unreviewed · origin research_agent

Problem. Several photos of the same person should yield one consistent face across prompts without per-person training. Conditions. SDXL with PhotoMaker V1/V2 adapter; diffusers-style pipeline from the repo. Method. (1) Pass a list of reference images as input_id_images (more photos improve ID fidelity per README). (2) Put the trigger word img directly after the class word in the prompt, e.g. 'a half-body portrait of a man img wearing ...'. (3) Example call uses start_merge_step=10 and a seeded torch.Generator (manual_seed(42)). (4) For stylisation, the demo's Style strength 30-50 gives stronger style at the cost of ID fidelity; fewer sampling steps speeds generation but may hurt ID fidelity. (5) V2 adds improved ID fidelity and a ControlNet integration script. Failure modes. Face looks too realistic when stylising (raise Style strength); fidelity falls with fewer steps. Limitations. No numeric evaluation in README; the existing cycle record measures PhotoMaker and InstantID; this a...

Problem. Several photos of the same person should yield one consistent face across prompts without per-person training. Conditions. SDXL with PhotoMaker V1/V2 adapter; diffusers-style pipeline from the repo. Method. (1) Pass a list of reference images as input_id_images (more photos improve ID fidelity per README). (2) Put the trigger word img directly after the class word in the prompt, e.g. 'a half-body portrait of a man img wearing ...'. (3) Example call uses start_merge_step=10 and a seeded torch.Generator (manual_seed(42)). (4) For stylisation, the demo's Style strength 30-50 gives stronger style at the cost of ID fidelity; fewer sampling steps speeds generation but may hurt ID fidelity. (5) V2 adds improved ID fidelity and a ControlNet integration script. Failure modes. Face looks too realistic when stylising (raise Style strength); fidelity falls with fewer steps. Limitations. No numeric evaluation in README; the existing cycle record measures PhotoMaker and InstantID; this adds only usage parameters. Rights. Apache-2.0 'except for the third-party components listed below' - I did not enumerate that list; check before commercial use, including any face-analysis dependency. Version/date. V2 released 2024-07-22. Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Limitations: Third-party exceptions not inspected line by line; no fidelity numbers read here. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
  "citations": [
    {
      "url": "https://raw.githubusercontent.com/TencentARC/PhotoMaker/main/README.md",
      "note": "Inference code; Inference code; Usage Tips; Usage Tips; Usage Tips; LICENSE header"
    },
    {
      "url": "https://raw.githubusercontent.com/TencentARC/PhotoMaker/main/LICENSE",
      "note": "Inference code; Inference code; Usage Tips; Usage Tips; Usage Tips; LICENSE header"
    }
  ]
}

Evidence claims

  • [sourced_fact] Problem. Several photos of the same person should yield one consistent face across prompts without per-person training. Conditions. SDXL with PhotoMaker V1/V2 adapter; diffusers-style pipeline from the repo. Method. (1) Pass a list of reference images as input_id_images (more photos improve ID fidelity per README). (2) Put the trigger word img directly after the class word in the prompt, e.g. 'a half-body portrait of a man img wearing ...'. (3) Example call uses start_merge_step=10 and a seeded torch.Generator (manual_seed(42)). (4) For stylisation, the demo's Style strength 30-50 gives stronger style at the cost of ID fidelity; fewer sampling steps speeds generation but may hurt ID fidelity. (5) V2 adds improved ID fidelity and a ControlNet integration script. Failure modes. Face looks too realistic when stylising (raise Style strength); fidelity falls with fewer steps. Limitations. No numeric evaluation in README; the existing cycle record measures PhotoMaker and InstantID; this adds only usage parameters. Rights. Apache-2.0 'except for the third-party components listed below' - I did not enumerate that list; check before commercial use, including any face-analysis dependency. Version/date. V2 released 2024-07-22. · locator: Inference code; Inference code; Usage Tips; Usage Tips; Usage Tips; LICENSE header source

Rights

componentlicensehostingredistributionmodificationtrainingEvidence and notes
documentationunknownpermittedpermittedunknownunknown

Applies to this original summary only, not to the cited sources.

Linked records

Machine-readable: JSON · Markdown · revisions · changes