huchenlei/ComfyUI_omost

Issues

• Could you update a installation......?

  #47 opened a day ago
  0

• About saving prompt words

  #46 opened 2 days ago
  9

• AttributeError: 'NoneType' object has no attribute 'cdequantize_blockwise_fp32'

  #45 opened 3 days ago
  0

• Is it possible to set canvas size?

  #44 opened 3 days ago
  1

• Please help me, KeyError: 'llama'

  #43 opened 5 days ago
  0

• 未来会支持SD3吗？

  #42 opened 5 days ago
  0

• prompt generation very slow

  #41 opened 6 days ago
  1

• whats the role of "omost greedy bags text embedding " node in comfyui?

  #39 opened 8 days ago
  1

• Hope to support SD3

  #38 opened 9 days ago
  0

• Hope mac arm support

  #37 opened 10 days ago
  1

• I hope to install an offline model

  #32 opened 12 days ago
  0

• The attention mask and the pad token id were not set. How do I fix it？

  #31 opened 13 days ago
  0

• Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`

  #30 opened 14 days ago
  1

• 这个节点后面会考虑加入多轮对话编辑图片吗？

  #29 opened 14 days ago
  1

• RuntimeError: Only Tensors of floating point and complex dtype can require gradients

  #24 opened 14 days ago
  2

• It doesn't seem like it's just me who doesn't know where the llm model should go.

  #23 opened 16 days ago
  1

• m1 max，No GPU found. A GPU is needed for quantization.

  #22 opened 16 days ago
  1

• Error occurred when executing OmostLLMLoaderNode:

  #21 opened 16 days ago
  0

• 加载phi报错

  #20 opened 16 days ago
  0

• 输入过长就报错

  #19 opened 16 days ago
  1

• 示范里的27k工作流里的[ImageFromBatch+]节点没办法找到

  #18 opened 16 days ago
  2

• AssertionError of `assert len(comfy_tokens) == 1`

  #16 opened 17 days ago
  1

• More Inference options

  #15 opened 17 days ago
  0

• Where are put in? about LLM models,lllyasviel/omost-llama-3-8b-4bits.

  #14 opened 17 days ago
  7

• Where do I put in/get the initial text for the LLM prompt?

  #13 opened 17 days ago
  1

• Is ConditioningSetMask used right for attention mask?

  #12 opened 17 days ago
  1

• ollama support?

  #11 opened 17 days ago
  0

• No package metadata was found for bitsandbytes

  #10 opened 16 days ago
  3

• 希望可以适配HunYuanDit大模型，更适合**宝宝

  #9 opened 17 days ago
  0

• Detected int4 weights but the version of bitsandbytes is not compatible with int4 serialization.

  #8 opened 17 days ago
  0

• Failed to import transformers.models.cohere.configuration_cohere because of the following error (look up to see its traceback): No module named 'transformers.models.cohere.configuration_cohere'

  #7 opened 17 days ago
  1

• how to use

  #6 opened 17 days ago
  1

• Error running "Omost LLM Loader"

  #5 opened 16 days ago
  5

• OmostLoadCanvasConditioningNode Error

  #4 opened 17 days ago
  4

• Guidance on Running Model Locally: Seeking Assistance

  #3 opened 18 days ago
  0

• 为啥我第三个节点和你的不一样

  #2 opened 18 days ago
  2

• Can I swtich another local LLM to drive the Omost conversation?

  #1 opened 18 days ago
  1