Forum Replies Created
-
Posts
-
It seems that the model is not loaded.
I just added the models to the notebook. Select Hunyuan or Wan_2_1 to load the model.
If it still doesn’t work, posting the error in console helps.
Video models tend to be much larger than image ones. They are just not made for Mac to run. While Mac’s silicon chip has gone a long way, the models must be rewritten to take full advantage of it. Even if a team manages to do that, there will still be a significant gap from Nvidia cards.
A1111 and Forge’s development is stagnant. Only ComfyUI is still going strong. In the foreseeable future, most new stuff will be on ComfyUI with an NVidia card (PC or Linux). If you don’t want to own one, the next option is using an online service, which is likely cheaper than owning one.
Yes, they kind of work but use the lowest controlnet strength you can get away with and release it early.
Haven’t encountered this before but you can try:
-
Use SDP Attention “–opt-sdp-attention” argument.
-
Forge uses a different backend. Try if you see the same error.
Not easy to coment on the specifics without an example, but you can:
- Test the same prompt on the SDXL 1.0 base model. It is well trained and can give you an ideal whether the juggernaut model has training issues.
- Whether it is due to the association effect https://stable-diffusion-art.com/courses/stable-diffusion-level-2/lessons/association-effect/
- Use negative prompt to supresss anything and settings you don’t want to see.
Yes it is possible but I want to keep the UI simple.
If there’s enough interest, I can create another notebook for downloading models to google drive.
-