20f5592077
Co-authored-by: zty624 <164896039+zty624@users.noreply.github.com> Co-authored-by: yhzx233 <16619108+yhzx233@users.noreply.github.com> Co-authored-by: Monalissaa <50078799+Monalissaa@users.noreply.github.com>
28 lines
1.5 KiB
JSON
28 lines
1.5 KiB
JSON
{
|
|
"schema_version": 2,
|
|
"model_repo": "OpenMOSS-Team/MOSS-Image-Base",
|
|
"model": "MOSS-Image-Base",
|
|
"parameters": {
|
|
"prompt": "A candid classroom photograph, slightly off-center, with a worn dark green chalkboard filling most of the frame. Uneven window light, soft shadows, chalk dust, eraser streaks, subtle camera grain. Visible board frame and chalk tray, a blurred desk corner in the foreground. Natural, slightly irregular white chalk handwriting—not polished typography or a flat blackboard graphic. Keep all text sharp, fully visible, and free of glare.\n\nThe chalkboard reads exactly:\n\n\"MOSS-Transcribe-Diarize is our flagship SOTA model family\nfor turning real-world long-form audio into structured,\nspeaker- aware transcripts in one pass. Instead of stitching\ntogether separate ASR and diarization systems, these\nmodels jointly perform speech transcription and speaker\ndiarization, producing time-aligned text with precise\ntimestamps and consistent speaker labels such as [S01], [S02], and beyond.\"",
|
|
"negative_prompt": "worst quality, bad anatomy, ugly face",
|
|
"height": 768,
|
|
"width": 1360,
|
|
"steps": 50,
|
|
"cfg": 3,
|
|
"shift": 6,
|
|
"num_images": 1,
|
|
"seed": 2051794908,
|
|
"uncond_skip_layers": "",
|
|
"slg_layers": "",
|
|
"slg_scale": 0,
|
|
"slg_start": 0,
|
|
"slg_stop": 1,
|
|
"max_sequence_length": 4096,
|
|
"offload": "none",
|
|
"compile_transformer": false
|
|
},
|
|
"sampler": "Euler",
|
|
"recovered_from": "Running Space gallery and example selection",
|
|
"image": "image.png"
|
|
}
|