ClipProj-MiniMax-H3 / demo /generation-settings.json
NicoLab28's picture
v3: calibrated against the stock 32B, image tokens for the 8B, demo folder
12a7266 verified
Raw
History Blame Contribute Delete
2.01 kB
{
"scene": "chess terrace",
"prompt_file": "chess-prompt.txt",
"note": "All five renders share every setting below. Only the projection changes. The pipeline is deterministic: running the same configuration twice produces identical decoded video and audio streams, verified by MD5.",
"settings": {
"aspect_ratio": "16:9 (Widescreen)",
"megapixels": 0.8,
"vae": [
"minimax_h3_audio_vae_fp32.safetensors",
"minimax_h3_video_vae_int8_convrot.safetensors"
],
"sampler": "res_multistep",
"steps": 8,
"scheduler": "simple",
"diffusion_model": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"seed": 42,
"fps": 24.0,
"turbo_lora": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"turbo_lora_strength": 1.0,
"upscale": "RTX Video Super Resolution 2.0x ULTRA",
"frames": 192,
"duration_seconds": 8.0,
"output_resolution": "2432x1344 after upscale"
},
"renders": [
{
"file": "chess-4b-ridge.mp4",
"text_encoder": "Qwen3-VL-4B",
"projection": "mmh3-4b-ClipProj-v3.safetensors"
},
{
"file": "chess-8b-ridge.mp4",
"text_encoder": "Qwen3-VL-8B",
"projection": "mmh3-8b-ClipProj-v3.safetensors"
},
{
"file": "chess-32b-reference.mp4",
"text_encoder": "Qwen3-VL-32B",
"projection": null
},
{
"file": "chess-8b-mlp.mp4",
"text_encoder": "Qwen3-VL-8B",
"projection": "mmh3-8b-ClipProj-v3-mlp.safetensors"
},
{
"file": "chess-4b-mlp.mp4",
"text_encoder": "Qwen3-VL-4B",
"projection": "mmh3-4b-ClipProj-v3-mlp.safetensors"
}
],
"comparison": {
"file": "chess-comparison.mp4",
"order": [
"chess-4b-ridge.mp4",
"chess-8b-ridge.mp4",
"chess-32b-reference.mp4",
"chess-8b-mlp.mp4",
"chess-4b-mlp.mp4"
],
"note": "Matrix-only first, then the 32B reference, then the residuals."
}
}