[DEBUG] main.cpp:689 - version: stable-diffusion.cpp version master-813-bfbef5b-u13b9d92, commit 13b9d92 ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97249 MiB): Device 0: NVIDIA RTX PRO 6000 Blackwell Server Edition, compute capability 12.0, VMM: yes, VRAM: 97249 MiB [DEBUG] main.cpp:690 - System Info: SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | AMX_INT8 = 1 | OPENMP = 1 | REPACK = 1 | [DEBUG] main.cpp:691 - SDCliParams { mode: vid_gen, output_path: "/tmp/h3-iq1/outputs/calibration.webm", image_path: "", metadata_format: "text", verbose: true, color: false, canny_preprocess: false, convert_name: false, preview_method: none, preview_interval: 1, preview_path: "preview.avi", preview_fps: 16, taesd_preview: false, preview_noisy: false, imatrix_out: "/tmp/h3-iq1/outputs/minimax_h3_fl2va_pruned.imatrix", metadata_raw: false, metadata_brief: false, metadata_all: false } [DEBUG] main.cpp:692 - SDContextParams { n_threads: 96, model_path: "", clip_l_path: "", clip_g_path: "", clip_vision_path: "", t5xxl_path: "", llm_path: "/tmp/h3-iq1/models/qwen3vl_32b_minimax_h3-Q2_K_M.gguf", llm_vision_path: "", diffusion_model_path: "/tmp/h3-iq1/models/minimax_h3_fl2va_pruned-Q8_0.gguf", high_noise_diffusion_model_path: "", uncond_diffusion_model_path: "", embeddings_connectors_path: "", vae_path: "/tmp/h3-iq1/models/vae/minimax_h3_video_vae_fp16.safetensors", vae_format: "auto", audio_vae_path: "", taesd_path: "", esrgan_path: "", control_net_path: "", embedding_dir: "", embeddings: { } wtype: NONE, tensor_type_rules: "", lora_model_dir: ".", hires_upscalers_dir: "", photo_maker_path: "", rng_type: cpu, sampler_rng_type: NONE, offload_params_to_cpu: false, max_vram: "0", stream_layers: false, eager_load: false, backend: "te=cpu", params_backend: "", split_mode: "", model_args: "", auto_fit: false, enable_mmap: false, control_net_cpu: false, clip_on_cpu: false, vae_on_cpu: false, flash_attn: false, diffusion_flash_attn: true, diffusion_conv_direct: false, vae_conv_direct: false, prediction: NONE, lora_apply_mode: auto, force_sdxl_vae_conv_scale: false } [DEBUG] main.cpp:693 - SDGenerationParams { loras: "{ }", high_noise_loras: "{ }", prompt: "A red panda walks along a mossy log in a misty forest, cinematic tracking shot, natural motion, detailed fur.", negative_prompt: "", ad_model_path: "", ad_prompt: "", ad_negative_prompt: "", extra_ad_args: "", clip_skip: -1, width: 320, height: 192, batch_count: 1, qwen_image_layers: 3, init_image_path: "", end_image_path: "", mask_image_path: "", control_image_path: "", ref_image_paths: [], ref_video_paths: [], ref_video_audio_paths: [], ref_audio_paths: [], control_video_path: "", auto_resize_ref_image: true, increase_ref_index: false, pm_id_images_dir: "", pm_id_embed_path: "", pm_style_strength: 20, skip_layers: [7, 8, 9], sample_params: (txt_cfg: 1.00, img_cfg: 1.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 4, eta: inf, shifted_timestep: 0, flow_shift: inf, extra_sample_args: ), high_noise_skip_layers: [7, 8, 9], high_noise_sample_params: (txt_cfg: 7.00, img_cfg: 7.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf, extra_sample_args: ), custom_sigmas: [], cache_mode: "", cache_option: "", cache: disabled (threshold=inf, start=0.15, end=0.95), moe_boundary: 0.875, video_frames: 5, fps: 16, vace_strength: 1, strength: 0.75, control_strength: 0.9, seed: 11, upscale_repeats: 1, upscale_tile_size: 128, hires: { enabled: false, upscaler: "Latent", model_path: "", scale: 2, target_width: 0, target_height: 0, steps: 0, denoising_strength: 0.7, custom_sigmas: [], upscale_tile_size: 128 }, vae_tiling_params: { 0, 0, 0, 0, 0.5, 0, 0, "" }, } [DEBUG] model_loader.cpp:228 - using 96 threads for model loading [INFO ] stable-diffusion.cpp:717 - loading diffusion model from '/tmp/h3-iq1/models/minimax_h3_fl2va_pruned-Q8_0.gguf' [INFO ] model_loader.cpp:236 - load /tmp/h3-iq1/models/minimax_h3_fl2va_pruned-Q8_0.gguf using gguf format [DEBUG] model_loader.cpp:288 - init from '/tmp/h3-iq1/models/minimax_h3_fl2va_pruned-Q8_0.gguf' [INFO ] stable-diffusion.cpp:774 - loading llm from '/tmp/h3-iq1/models/qwen3vl_32b_minimax_h3-Q2_K_M.gguf' [INFO ] model_loader.cpp:236 - load /tmp/h3-iq1/models/qwen3vl_32b_minimax_h3-Q2_K_M.gguf using gguf format [DEBUG] model_loader.cpp:288 - init from '/tmp/h3-iq1/models/qwen3vl_32b_minimax_h3-Q2_K_M.gguf' [INFO ] stable-diffusion.cpp:788 - loading vae from '/tmp/h3-iq1/models/vae/minimax_h3_video_vae_fp16.safetensors' [INFO ] model_loader.cpp:242 - load /tmp/h3-iq1/models/vae/minimax_h3_video_vae_fp16.safetensors using safetensors format [DEBUG] model_loader.cpp:316 - init from '/tmp/h3-iq1/models/vae/minimax_h3_video_vae_fp16.safetensors', prefix = 'vae.' [INFO ] stable-diffusion.cpp:905 - Version: MiniMax-H3 [DEBUG] ggml_extend_backend.cpp:545 - Found 2 backend devices: [DEBUG] ggml_extend_backend.cpp:548 - #0: CUDA0 [DEBUG] ggml_extend_backend.cpp:548 - #1: CPU [DEBUG] ggml_extend_backend.cpp:395 - Initializing backend: CUDA0 [INFO ] stable-diffusion.cpp:956 - Weight type stat: f32: 8 | f16: 664 | q8_0: 210 | q2_K: 300 | q5_K: 50 | bf16: 764 [INFO ] stable-diffusion.cpp:957 - Conditioner weight type stat: q2_K: 300 | q5_K: 50 | bf16: 552 [INFO ] stable-diffusion.cpp:958 - Diffusion model weight type stat: f32: 8 | f16: 102 | q8_0: 210 | bf16: 212 [INFO ] stable-diffusion.cpp:959 - VAE weight type stat: f16: 562 [DEBUG] stable-diffusion.cpp:961 - ggml tensor size = 432 bytes [DEBUG] ggml_extend_backend.cpp:395 - Initializing backend: CPU [DEBUG] qwen2_tokenizer.cpp:14 - merges size 151387 [DEBUG] qwen2_tokenizer.cpp:39 - vocab size: 151674 [DEBUG] llm.hpp:286 - llm: num_layers = 50, vocab_size = 151936, hidden_size = 5120, intermediate_size = 25600 [DEBUG] llm.hpp:1768 - enable llm vision [DEBUG] minimax_h3.hpp:109 - minimax_h3: layers=50, hidden=5376, heads=56, head_dim=128, ffn=14336, adaln_curve=1025 [INFO ] stable-diffusion.cpp:1494 - using VAE for encoding / decoding [INFO ] stable-diffusion.cpp:1619 - Using flash attention in the diffusion model [DEBUG] stable-diffusion.cpp:1627 - validating model metadata [DEBUG] stable-diffusion.cpp:1686 - model metadata validated; weights will be prepared lazily [INFO ] stable-diffusion.cpp:1727 - total params memory size = 39497.75MB (VRAM 25511.91MB, RAM 13985.83MB): text_encoders 13985.83MB(RAM), diffusion_model 20530.93MB(VRAM), vae 4980.99MB(VRAM), controlnet 0.00MB(N/A), extensions 0.00MB(N/A) [INFO ] stable-diffusion.cpp:1846 - running in FLOW mode [WARN ] stable-diffusion.cpp:4092 - MiniMax-H3 uses 24 fps; overriding requested fps 16 [INFO ] denoiser.hpp:1051 - get_sigmas with discrete scheduler [INFO ] stable-diffusion.cpp:4365 - sampling using Euler method [DEBUG] conditioner.hpp:1987 - parse 'A red panda walks along a mossy log in a misty forest, cinematic tracking shot, natural motion, detailed fur.' to [['A red panda walks along a mossy log in a misty forest, cinematic tracking shot, natural motion, detailed fur.', 1], ] [DEBUG] bpe_tokenizer.cpp:208 - split prompt "A red panda walks along a mossy log in a misty forest, cinematic tracking shot, natural motion, detailed fur." to 25 tokens ["A", "Ġred", "Ġpanda", "Ġwalks", "Ġalong", "Ġa", "Ġmoss", "y", "Ġlog", "Ġin", "Ġa", "Ġmist", "y", "Ġforest", ",", "Ġcinematic", "Ġtracking", "Ġshot", ",", "Ġnatural", "Ġmotion", ",", "Ġdetailed", "Ġfur", ".", ] [DEBUG] model_loader.cpp:1042 - loading 551/902 tensors from /tmp/h3-iq1/models/qwen3vl_32b_minimax_h3-Q2_K_M.gguf |########## | 103/551 - 849.18MB/s |###################################### | 411/551 - 15.50GB/s |##################################################| 541/551 - 13.63GB/s |##################################################| 551/551 - 4.12GB/s [INFO ] model_loader.cpp:1304 - loading tensors completed, taking 2.69s (read: 0.42s, memcpy: 0.00s, convert: 0.01s, copy_to_backend: 0.00s) [DEBUG] model_manager.cpp:406 - model manager prepared params backend buffer (12844.50 MB, 551 tensors, RAM) [DEBUG] ggml_extend.hpp:2193 - qwen3vl compute buffer size: 5.86 MB(RAM) [DEBUG] conditioner.hpp:2882 - computing condition graph completed, taking 5144 ms [INFO ] stable-diffusion.cpp:6537 - get_learned_condition completed, taking 5.14s [INFO ] stable-diffusion.cpp:6899 - generate_video 320x192x5 [DEBUG] stable-diffusion.cpp:6964 - sample 20x12x2 [DEBUG] model_loader.cpp:1042 - loading 532/532 tensors from /tmp/h3-iq1/models/minimax_h3_fl2va_pruned-Q8_0.gguf |###################### | 230/532 - 1.25GB/s |######################## | 250/532 - 1.52GB/s |######################### | 265/532 - 1.79GB/s |############################ | 289/532 - 2.92GB/s |############################## | 314/532 - 4.34GB/s |################################ | 333/532 - 5.38GB/s |################################# | 349/532 - 5.97GB/s |################################### | 364/532 - 6.44GB/s |##################################### | 393/532 - 6.75GB/s |########################################## | 438/532 - 6.98GB/s |############################################### | 497/532 - 7.22GB/s |##################################################| 532/532 - 7.67GB/s [INFO ] model_loader.cpp:1304 - loading tensors completed, taking 2.60s (read: 0.10s, memcpy: 0.00s, convert: 0.00s, copy_to_backend: 1.97s) [DEBUG] model_manager.cpp:406 - model manager prepared params backend buffer (20530.96 MB, 532 tensors, VRAM) [DEBUG] ggml_extend.hpp:2193 - minimax_h3 compute buffer size: 45.15 MB(VRAM) |============> | 1/4 - 3.55s/it |=========================> | 2/4 - 1.96it/s |=====================================> | 3/4 - 1.94it/s |==================================================| 4/4 - 1.98it/s [INFO ] stable-diffusion.cpp:6997 - sampling completed, taking 5.08s [INFO ] stable-diffusion.cpp:7140 - generating latent video completed, taking 5.08s [DEBUG] stable-diffusion.cpp:6559 - decode_video_outputs latent 20x12x2x24 [DEBUG] vae.hpp:190 - VAE Tile size: 16x12 [DEBUG] ggml_extend.hpp:884 - num tiles : 2, 1 [DEBUG] ggml_extend.hpp:885 - optimal overlap : 0.750000, 0.000000 (targeting 0.250000) [DEBUG] ggml_extend.hpp:886 - processing 2 tiles [DEBUG] model_loader.cpp:1042 - loading 441/562 tensors from /tmp/h3-iq1/models/vae/minimax_h3_video_vae_fp16.safetensors |############################### | 269/441 - 4.93GB/s |########################################### | 375/441 - 5.99GB/s |##################################################| 441/441 - 8.12GB/s [INFO ] model_loader.cpp:1304 - loading tensors completed, taking 0.56s (read: 0.02s, memcpy: 0.00s, convert: 0.00s, copy_to_backend: 0.41s) [DEBUG] model_manager.cpp:406 - model manager prepared params backend buffer (4636.94 MB, 441 tensors, VRAM) [DEBUG] ggml_extend.hpp:2193 - minimax_h3_video_vae compute buffer size: 307.03 MB(VRAM) |=========================> | 1/2 - 1.28it/s |==================================================| 2/2 - 5.46it/s [DEBUG] vae.hpp:220 - computing vae decode graph completed, taking 0.97s [INFO ] stable-diffusion.cpp:6568 - decode_first_stage completed, taking 0.97s [DEBUG] stable-diffusion.cpp:6573 - decode_video_outputs decoded 320x192x5x3 [INFO ] stable-diffusion.cpp:7200 - generate_video completed in 11.20s [DEBUG] model_manager.cpp:981 - model manager releasing params backend buffer (12844.50 MB, 551 tensors, RAM) [DEBUG] model_manager.cpp:981 - model manager releasing params backend buffer (20530.96 MB, 532 tensors, VRAM) [DEBUG] model_manager.cpp:981 - model manager releasing params backend buffer (4636.94 MB, 441 tensors, VRAM) [INFO ] main.cpp:536 - save result video to '/tmp/h3-iq1/outputs/calibration.webm' [INFO ] main.cpp:1016 - saving imatrix to '/tmp/h3-iq1/outputs/minimax_h3_fl2va_pruned.imatrix'