SEED-Story: multimodal long story generation with an LLM
Source: https://github.com/tencentarc/seed-story
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "MLLM that writes long interleaved text-and-image stories with consistent characters and style; releases the StoryStream dataset and model on Hugging Face.",
"source_type": "repository",
"availability": "available",
"source_owner": "Tencent ARC Lab",
"next_check_at": "2026-11-16T00:00:00.000Z",
"hardware_notes": "Not checked.",
"upstream_updated_at": "2024-10-11T08:44:17.000Z"
}Evidence claims
- [sourced_fact] README: SEED-Story is a multimodal LLM generating long stories with coherent narrative text and character- and style-consistent images, built on SEED-X; links model and StoryStream dataset on Hugging Face. · locator: README header source
- [sourced_fact] Repository license file states Seed-Story is licensed under Apache-2.0 except for listed third-party components. · locator: license_Seed-Story.txt header source
- [upstream_claim] Paper abstract frames multimodal story generation as interleaved image-text with long coherent sequences as the challenge. · locator: abstract source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | Apache-2.0 | permitted | permitted | permitted | unknown | Apache-2.0 'except for the third-party components listed' in the license file (list not reviewed). GitHub detection shows NOASSERTION. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Weights on Hugging Face; license not checked. |
| dataset | unknown | unknown | unknown | unknown | unknown | StoryStream dataset on Hugging Face; license not checked. |