huchenlei/ComfyUI_omost

Issues

• Http Local server

  #61 opened 18 days ago by Khampol
  1

• 怎么才能把数据传递给Omost 加载背景条件的json串

  #60 opened a month ago by HiyungXu
  0

• i got this issus about ComfyUI_omost.omost_nodes - ERROR

  #52 opened 4 months ago by zmczmc123654
  1

• ollama support?

  #11 opened 6 months ago by jesenzhang
  1

• More examples? Workflows

  #59 opened a month ago by ClothingAI
  0

• Error occurred when executing OmostLLMLoaderNode:

  #21 opened 6 months ago by liaosu0755
  1

• 您好，喜欢这个项目，但发现与目前的FLUX不兼容

  #58 opened 3 months ago by wuliang19869312
  0

• 运行LLMchat无结果Running LLMchat yields no results

  #57 opened 3 months ago by Eikwang
  0

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

  #14 opened 6 months ago by focusline2023
  9

• 要是flux能用就好了

  #56 opened 3 months ago by zergqyue
  0

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

  #45 opened 5 months ago by jadechip
  2

• 通过llama.cpp对omost-llama-3-8b-Q8_0-GGUF进行加速时GPU显存使用率很低，没有用到。

  #55 opened 4 months ago by zk19971101
  0

• Achieving llama.cpp Speed with Lower VRAM Requirements using llama-cpp-python

  #53 opened 4 months ago by Rio77Shiina
  0

• How to running text-generation-ifenrence(TGI) with downloaded model parameters?

  #50 opened 4 months ago by zk19971101
  0

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

  #22 opened 6 months ago by yiwangsimple
  2

• Getting error: Cannot import name 'OpenAI' from "openai'

  #49 opened 5 months ago by Duemellon
  0

• I hope to install an offline model

  #32 opened 6 months ago by smae08
  1

• Please help me, KeyError: 'llama'

  #43 opened 5 months ago by Kevinjuly
  1

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

  #47 opened 5 months ago by K-O-N-B
  1

• help me

  #48 opened 5 months ago by Llin1028
  0

• About saving prompt words

  #46 opened 5 months ago by smae08
  9

• Hope mac arm support

  #37 opened 5 months ago by alexcc4
  1

• Is it possible to set canvas size?

  #44 opened 5 months ago by elphamale
  1

• 未来会支持SD3吗？

  #42 opened 5 months ago by dk19930125
  0

• prompt generation very slow

  #41 opened 5 months ago by sipie800
  1

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

  #39 opened 5 months ago by yatoubusha
  1

• Hope to support SD3

  #38 opened 5 months ago by FLYleoYBQ
  0

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

  #23 opened 6 months ago by chenpipi0807
  1

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

  #31 opened 6 months ago by zoenders
  0

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

  #30 opened 6 months ago by satangel2222
  1

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

  #24 opened 6 months ago by wildage
  2

• 这个节点后面会考虑加入多轮对话编辑图片吗？

  #29 opened 6 months ago by MoonDownHugo
  1

• OmostLoadCanvasConditioningNode Error

  #4 opened 6 months ago by MrGingerSir
  4

• More Inference options

  #15 opened 6 months ago by zdaar
  0

• 输入过长就报错

  #19 opened 6 months ago by ailfreedom
  1

• 加载phi报错

  #20 opened 6 months ago by caissonfiv
  0

• Error running "Omost LLM Loader"

  #5 opened 6 months ago by xiao-ning-ning
  5

• No package metadata was found for bitsandbytes

  #10 opened 6 months ago by ziziguai
  3

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

  #18 opened 6 months ago by dxyklp
  2

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

  #13 opened 6 months ago by Duemellon
  1

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

  #16 opened 6 months ago by mymusise
  1

• Is ConditioningSetMask used right for attention mask?

  #12 opened 6 months ago by wuutiing
  1

• 希望可以适配HunYuanDit大模型，更适合**宝宝

  #9 opened 6 months ago by FLYleoYBQ
  0

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

  #8 opened 6 months ago by Cladislav
  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 6 months ago by alenhrp
  1

• how to use

  #6 opened 6 months ago by CJT666
  1

• Guidance on Running Model Locally: Seeking Assistance

  #3 opened 6 months ago by supca
  0

• 为啥我第三个节点和你的不一样

  #2 opened 6 months ago by linjian-ufo
  2

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

  #1 opened 6 months ago by kelvinyoung
  1