new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

bytedance/models

6 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

ByteDance image models via factory method

ByteDance Seedream image models are created using the `.image()` factory method on the provider instance.

ByteDance image model identification

ByteDance identifies Seedream models by their ModelArk model id (e.g. `seedream-5-0-260128`) or an account-specific endpoint id (e.g. `ep-...`).

ByteDance image model capabilities table

Image models and capabilities: | Model | Model ID | Capabilities | |-------|----------|---------------| | Seedream 5.0 Pro | `dola-seedream-5-0-pro-260628` | Text-to-image, single/multi image-to-image, interactive editing (markers). Sizes: 1K, 2K. Formats: png, jpeg. Up to 10 references. | | Seedream 5.0 Lite | `seedream-5-0-260128` (alias `seedream-5-0-lite-260128`) | Text-to-image, single/multi image-to-image, batch generation. Sizes: 2K, 3K, 4K. Formats: png, jpeg. Up to 14 references. | | Seedream 4.5 | `seedream-4-5-251128` | Text-to-image, single/multi image-to-image, batch generation. Sizes: 2K, 4K. Format: jpeg. Up to 14 references. | | Seedream 4.0 | `seedream-4-0-250828` | Text-to-image, single/multi image-to-image, batch generation, fast prompt mode. Sizes: 1K, 2K, 4K. Format: jpeg. Up to 14 references. |

ByteDance video models via factory method

ByteDance video models are created using the `.video()` factory method on the provider instance.

ByteDance video model capabilities table

Video models and capabilities: | Model | Model ID | Capabilities | |-------|----------|---------------| | Seedance 2.0 | `dreamina-seedance-2-0-260128` | T2V, I2V, reference videos (up to 3), reference audio (up to 3), audio-video sync. Duration: 4-15s. Resolution: 480p, 720p. | | Seedance 2.0 Fast | `dreamina-seedance-2-0-fast-260128` | T2V, I2V, reference videos (up to 3), reference audio (up to 3), audio-video sync. Optimized for speed. Duration: 4-15s. Resolution: 480p, 720p. | | Seedance 1.5 Pro | `seedance-1-5-pro-251215` | T2V, I2V (first frame), I2V (first+last frame), audio-video sync, draft mode. Duration: 4-12s. Resolution: 480p, 720p, 1080p. | | Seedance 1.0 Pro | `seedance-1-0-pro-250528` | T2V, I2V (first frame), I2V (first+last frame). Duration: 2-12s. Resolution: 480p, 720p, 1080p. | | Seedance 1.0 Pro Fast | `seedance-1-0-pro-fast-251015` | T2V, I2V (first frame). Optimized for speed and cost. Duration: 2-12s. | | Seedance 1.0 Lite (T2V) | `seedance-1-0-lite-t2v-250428` | Text-to-video only. Duration: 2-12s. Resolution: 480p, 720p, 1080p. | | Seedance 1.0 Lite (I2V) | `seedance-1-0-lite-i2v-250428` | I2V (first frame), I2V (first+last frame), multi-reference images (1-4). Duration: 2-12s. Resolution: 480p, 720p. |

ByteDance custom model IDs

Any model ID string can be passed if needed for future models not yet documented, including future image and video models or custom endpoint IDs.

Give your agent this brain