跳转至内容
  • 版块
  • 最新
  • 标签
  • 热门
  • 用户
  • 群组
皮肤
  • 浅色
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • 深色
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • 默认(LCZ-Blue)
  • 不使用皮肤
  • LCZ-Green
  • LCZ-Blue
  • LCZ-Black
折叠
品牌标识

抡锤者

首页 版块 标签
硬件
装备秀
AI 广场 App
  1. 主页
  2. 版块
  3. AI音视频画图
  4. 【H3剑心比赛】[9060XT 16GB]雖然我們短一點小一點,也是可以玩的~~低解析(1280*736)/9s

【H3剑心比赛】[9060XT 16GB]雖然我們短一點小一點,也是可以玩的~~低解析(1280*736)/9s

已定时 已固定 已锁定 已移动 AI音视频画图
rx9060xtminimax视频生成
5 帖子 3 发布者 144 浏览
  • 从旧到新
  • 从新到旧
  • 最多赞同
回复
  • 在新帖中回复
登录后回复
此主题已被删除。只有拥有主题管理权限的用户可以查看。
  • 先生陳先
    先生陳先
    先生陳
    编写于 最后由 terry 编辑
    #1

    什麼加速都不用! 9060XT 便宜治百病,也可以玩玩哦~~為什麼有幾個大佬的聲音有雜音?
    一段影片15分鐘內,還可接受,太長了等不了。

    H3剑心2D风格
    Youtube Video

    [INFO] got prompt
    [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\vae\minimax_h3_audio_vae_fp32.safetensors']
    [INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
    [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\vae\minimax_h3_sol_vae_int8_convrot.safetensors']
    [INFO] Found quantization metadata version 1
    [INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
    [INFO] Found quantization metadata version 1
    [INFO] Using MixedPrecisionOps for text encoder
    [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\text_encoders\qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors']
    [INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
    [INFO] Requested to load MiniMaxH3VideoVAE
    [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
    [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
    [INFO] Requested to load MiniMaxH3TEModel_
    [INFO] Model MiniMaxH3TEModel_ prepared for dynamic VRAM loading. 14956MB Staged. 0 patches attached. Force pre-loaded 410 weights: 4572 KB.
    [INFO] got prompt
    [INFO] FETCH ComfyRegistry Data [DONE]
    [INFO] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
    FETCH DATA from: D:\comfyui-rocm\user__manager\cache\3351870820_custom-node-list.json
    [DONE]
    [INFO] [ComfyUI-Manager] All startup tasks have been completed.
    [INFO] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
    [INFO] model_type FLOW_AV
    [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\diffusion_models\minimax_h3_ref2va_pruned_bf16.safetensors']
    [INFO] Requested to load MiniMaxH3
    [INFO] 0 models unloaded.
    [INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19308MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB.
    0%| | 0/5 [00:00<?, ?it/s]
    0%| | 0/5 [00:00<?, ?it/s, Model Initializing ... ]
    0%| | 0/5 [02:33<?, ?it/s, Model Initialization complete! ]
    20%|██ | 1/5 [02:33<10:14, 153.73s/it, Model Initialization complete! ]
    [INFO] got prompt
    20%|██ | 1/5 [04:50<10:14, 153.73s/it]
    40%|████ | 2/5 [04:50<07:15, 145.05s/it]
    60%|██████ | 3/5 [07:14<04:49, 144.71s/it]
    80%|████████ | 4/5 [09:39<02:24, 144.93s/it]
    100%|██████████| 5/5 [12:04<00:00, 144.59s/it]
    100%|██████████| 5/5 [12:04<00:00, 144.87s/it]
    [INFO] Comfy model compiler graph breaks: 0, rogues: 0
    [INFO] Requested to load MiniMaxH3AudioVAE
    [INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
    [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
    [FFmpegUpscale2x] 226 frame(s) 1280x736 -> 1920x1080 (scale=2.0, width=1920, height=1080, filter=lanczos, denoise=0.0, sharpen=0.0, deband=False, grain=0, ffmpeg=F:\ffmpeg\bin\ffmpeg.exe)
    [INFO] Prompt executed in 00:14:24
    [INFO] Using LRU cache

    3D
    H3剑心3D风格
    Youtube Video

    [INFO] got prompt
    [INFO] FETCH ComfyRegistry Data [DONE]
    [INFO] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
    FETCH DATA from: D:\comfyui-rocm\user__manager\cache\3351870820_custom-node-list.json
    [DONE]
    [INFO] [ComfyUI-Manager] All startup tasks have been completed.
    [INFO] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
    [INFO] model_type FLOW_AV
    [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\diffusion_models\minimax_h3_ref2va_pruned_bf16.safetensors']
    [INFO] Requested to load MiniMaxH3
    [INFO] 0 models unloaded.
    [INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19308MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB.
    0%| | 0/5 [00:00<?, ?it/s]
    0%| | 0/5 [00:00<?, ?it/s, Model Initializing ... ]
    0%| | 0/5 [02:33<?, ?it/s, Model Initialization complete! ]
    20%|██ | 1/5 [02:33<10:14, 153.73s/it, Model Initialization complete! ]
    [INFO] got prompt
    20%|██ | 1/5 [04:50<10:14, 153.73s/it]
    40%|████ | 2/5 [04:50<07:15, 145.05s/it]
    60%|██████ | 3/5 [07:14<04:49, 144.71s/it]
    80%|████████ | 4/5 [09:39<02:24, 144.93s/it]
    100%|██████████| 5/5 [12:04<00:00, 144.59s/it]
    100%|██████████| 5/5 [12:04<00:00, 144.87s/it]
    [INFO] Comfy model compiler graph breaks: 0, rogues: 0
    [INFO] Requested to load MiniMaxH3AudioVAE
    [INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
    [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
    [FFmpegUpscale2x] 226 frame(s) 1280x736 -> 1920x1080 (scale=2.0, width=1920, height=1080, filter=lanczos, denoise=0.0, sharpen=0.0, deband=False, grain=0, ffmpeg=F:\ffmpeg\bin\ffmpeg.exe)
    [INFO] Prompt executed in 00:14:24

    image.jpeg

    perterP 1 条回复 最后回复
    1
    • terryT
      terryT
      terry
      易有太极
      编写于 最后由 terry 编辑
      #2

      你直接去参赛不好吗,修改下标题,我给你参赛。做的不错。

      油管:https://www.youtube.com/@抡锤者

      1 条回复 最后回复
      0
      • 先生陳先 先生陳

        什麼加速都不用! 9060XT 便宜治百病,也可以玩玩哦~~為什麼有幾個大佬的聲音有雜音?
        一段影片15分鐘內,還可接受,太長了等不了。

        H3剑心2D风格
        Youtube Video

        [INFO] got prompt
        [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\vae\minimax_h3_audio_vae_fp32.safetensors']
        [INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
        [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\vae\minimax_h3_sol_vae_int8_convrot.safetensors']
        [INFO] Found quantization metadata version 1
        [INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
        [INFO] Found quantization metadata version 1
        [INFO] Using MixedPrecisionOps for text encoder
        [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\text_encoders\qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors']
        [INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
        [INFO] Requested to load MiniMaxH3VideoVAE
        [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
        [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
        [INFO] Requested to load MiniMaxH3TEModel_
        [INFO] Model MiniMaxH3TEModel_ prepared for dynamic VRAM loading. 14956MB Staged. 0 patches attached. Force pre-loaded 410 weights: 4572 KB.
        [INFO] got prompt
        [INFO] FETCH ComfyRegistry Data [DONE]
        [INFO] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
        FETCH DATA from: D:\comfyui-rocm\user__manager\cache\3351870820_custom-node-list.json
        [DONE]
        [INFO] [ComfyUI-Manager] All startup tasks have been completed.
        [INFO] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
        [INFO] model_type FLOW_AV
        [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\diffusion_models\minimax_h3_ref2va_pruned_bf16.safetensors']
        [INFO] Requested to load MiniMaxH3
        [INFO] 0 models unloaded.
        [INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19308MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB.
        0%| | 0/5 [00:00<?, ?it/s]
        0%| | 0/5 [00:00<?, ?it/s, Model Initializing ... ]
        0%| | 0/5 [02:33<?, ?it/s, Model Initialization complete! ]
        20%|██ | 1/5 [02:33<10:14, 153.73s/it, Model Initialization complete! ]
        [INFO] got prompt
        20%|██ | 1/5 [04:50<10:14, 153.73s/it]
        40%|████ | 2/5 [04:50<07:15, 145.05s/it]
        60%|██████ | 3/5 [07:14<04:49, 144.71s/it]
        80%|████████ | 4/5 [09:39<02:24, 144.93s/it]
        100%|██████████| 5/5 [12:04<00:00, 144.59s/it]
        100%|██████████| 5/5 [12:04<00:00, 144.87s/it]
        [INFO] Comfy model compiler graph breaks: 0, rogues: 0
        [INFO] Requested to load MiniMaxH3AudioVAE
        [INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
        [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
        [FFmpegUpscale2x] 226 frame(s) 1280x736 -> 1920x1080 (scale=2.0, width=1920, height=1080, filter=lanczos, denoise=0.0, sharpen=0.0, deband=False, grain=0, ffmpeg=F:\ffmpeg\bin\ffmpeg.exe)
        [INFO] Prompt executed in 00:14:24
        [INFO] Using LRU cache

        3D
        H3剑心3D风格
        Youtube Video

        [INFO] got prompt
        [INFO] FETCH ComfyRegistry Data [DONE]
        [INFO] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
        FETCH DATA from: D:\comfyui-rocm\user__manager\cache\3351870820_custom-node-list.json
        [DONE]
        [INFO] [ComfyUI-Manager] All startup tasks have been completed.
        [INFO] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
        [INFO] model_type FLOW_AV
        [INFO] Model storage policy: fast_disk=True paths=['D:\Comfy-Desktop\models\diffusion_models\minimax_h3_ref2va_pruned_bf16.safetensors']
        [INFO] Requested to load MiniMaxH3
        [INFO] 0 models unloaded.
        [INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19308MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB.
        0%| | 0/5 [00:00<?, ?it/s]
        0%| | 0/5 [00:00<?, ?it/s, Model Initializing ... ]
        0%| | 0/5 [02:33<?, ?it/s, Model Initialization complete! ]
        20%|██ | 1/5 [02:33<10:14, 153.73s/it, Model Initialization complete! ]
        [INFO] got prompt
        20%|██ | 1/5 [04:50<10:14, 153.73s/it]
        40%|████ | 2/5 [04:50<07:15, 145.05s/it]
        60%|██████ | 3/5 [07:14<04:49, 144.71s/it]
        80%|████████ | 4/5 [09:39<02:24, 144.93s/it]
        100%|██████████| 5/5 [12:04<00:00, 144.59s/it]
        100%|██████████| 5/5 [12:04<00:00, 144.87s/it]
        [INFO] Comfy model compiler graph breaks: 0, rogues: 0
        [INFO] Requested to load MiniMaxH3AudioVAE
        [INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
        [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 1895MB Staged. 0 patches attached. Force pre-loaded 104 weights: 251 KB.
        [FFmpegUpscale2x] 226 frame(s) 1280x736 -> 1920x1080 (scale=2.0, width=1920, height=1080, filter=lanczos, denoise=0.0, sharpen=0.0, deband=False, grain=0, ffmpeg=F:\ffmpeg\bin\ffmpeg.exe)
        [INFO] Prompt executed in 00:14:24

        image.jpeg

        perterP
        perterP
        perter
        王侯将相
        编写于 最后由 编辑
        #3

        @先生陳 说:

        minimax_h3_ref2va_pruned_bf16.safetensors

        bf16满血的模型的确效果要好很多,显存大的还是要上满血模型。

        1 条回复 最后回复
        0
        • 先生陳先
          先生陳先
          先生陳
          编写于 最后由 编辑
          #4

          不過我是用fp8,16gb是小的
          感謝站長過不合比賽規格看就好了
          Youtube Video

          1 条回复 最后回复
          0
          • terryT
            terryT
            terry
            易有太极
            编写于 最后由 terry 编辑
            #5

            你后加这个还不如前面的 ,过审。我帮你改下标题,20分奖励到手。这次比赛看的是大家如何调教手里的硬件,而不是只看效果。不过既然提前说死了1344 * 768,你就到此为止了。以后会更灵活。

            油管:https://www.youtube.com/@抡锤者

            1 条回复 最后回复
            0

            你好!看起来您对这段对话很感兴趣,但您还没有一个账号。

            厌倦了每次访问都刷到同样的帖子?您注册账号后,您下次访问时都将自动回到上次浏览的位置,并可选择接收新回复的通知(通过电子邮件或推送通知)。您还可以收藏帖子、为帖子点赞,以此向其他社区成员表达您的感谢。

            有了你的建议,这篇帖子会更精彩哦 💗

            注册 登录
            回复
            • 在新帖中回复
            登录后回复
            • 从旧到新
            • 从新到旧
            • 最多赞同


            • 登录

            • 登录或注册以进行搜索。
            • 第一个帖子
              最后一个帖子
            0
            • 版块
            • 最新
            • 标签
            • 热门
            • 用户
            • 群组