custom merge with low-step loras. base model: https://huggingface.co/Freepik/flux.1-lite-8B-alpha
1080p picture with 4 steps takes 10 seconds on a 4070 ti
currently working only in comfyui via load diffusion model node.
works with some loras, but not all.
PuLID not working.
Description
FAQ
Comments (8)
How to run this model in Forge A1111?
forge currently not supported this model
i have this error on Forge:
TypeError: linear(): argument 'weight' (position 2) must be Tensor, not NoneType
проверил, в forge эта модель не работает, только в comfyui. обновил описание.
@DooFY87 Только буду учиться работать в комфи, можешь пожалуйста выложить скриншот со схемой которую там надо сделать для этьой модели.
@DooFY87 А еще лучше файл с готовым шаблоном для комфи.
@Valer4ikSheva вот шаблон https://dropmefiles.com/mh4JB
I really like your conversion of the rapid WAN 2.2 model; I've also downloaded a quantified conversion model. However, after the conversion, the model doesn't work properly. Could you please share your conversion method, or the software you used? Thank you.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.