Amazon90
Amazon90
### Your question In the newly released workflow 'Wan2.1 Fun Control Workflow', is there a detailed explanation about how to use the 'SkipLayerGuidanceDiT' and 'UNetTemporalAttentionMultiply' nodes?  ### Logs ```powershell...
### Description https://huggingface.co/PaddlePaddle/PaddleOCR-VL ### Application Scenario The model delivers more precise image-to-text outputs. ### References _No response_
I’d like to ask whether LayerDiffuse is compatible with any SDXL-based models (such as Pony, Illustrious, Noobai), or if it only works with the official standard SDXL model.
Hi, this app is great! Could you please add support for Android TV?
Can these models from the following folders: — models--amphion--MaskGCT, — models--facebook--w2v-bert-2.0, — models--funasr--campplus, — models--nvidia--bigvgan_v2_22khz_80band_256x, be placed directly under "index-tts\checkpoints" instead of being downloaded to the Hugging Face cache directory...
Pulid Flux performs well in text-to-image generation but underperforms in image-to-image tasks. However, when used in RF Inversion, Pulid delivers better face-swapping results compared to Face Detailer. That said, I...
`[2025-08-23] 🚀 v1.0.0 adds support for [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image)! Check [this workflow](https://github.com/nunchaku-tech/ComfyUI-nunchaku/blob/main/example_workflows/nunchaku-qwen-image.json) to get started. LoRA support is coming soon.` May I ask if ComfyUI Nunchaku currently supports arbitrary LoRA models for...
I noticed that all the ComfyUI support you mentioned in the README is based on wrapper nodes using the Diffusers library, which forces users to download large Diffusers-format versions of...
``` [JoyCaption] ℹ️ No custom models found, skipping user-defined HF models. [JoyCaption GGUF] ℹ️ No custom models found, skipping user-defined GGUF models. ``` I noticed your custom JoyCaption node supports...
Requesting Sora sharding or routing configuration