Update README.md (#7)
Browse files- Update README.md (87ab607396894022fc7d48439bf70dc77a059937)
Co-authored-by: Yanzuo Lu <[email protected]>
README.md
CHANGED
@@ -18,10 +18,11 @@ Project Page: https://hyper-sd.github.io/
|
|
18 |
|
19 |
## News🔥🔥🔥
|
20 |
|
21 |
-
* Apr.
|
22 |
-
* Apr.
|
23 |
* Apr.23, 2024. Our technical report 📚 is uploaded to [arXiv](https://arxiv.org/abs/2404.13686)! Many implementation details are provided and we welcome more discussions👏.
|
24 |
-
* Apr.
|
|
|
25 |
|
26 |
## Try our Hugging Face demos:
|
27 |
Hyper-SD Scribble demo host on [🤗 scribble](https://huggingface.co/spaces/ByteDance/Hyper-SD15-Scribble)
|
@@ -316,9 +317,12 @@ image = pipe("a blue paradise bird in the jungle", num_inference_steps=1, image=
|
|
316 |
image.save('image_out.png')
|
317 |
```
|
318 |
## Comfyui Usage
|
319 |
-
* `Hyper-SDXL-Nstep-lora.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SDXL-Nsteps-lora-workflow.json)
|
320 |
* `Hyper-SD15-Nstep-lora.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SD15-Nsteps-lora-workflow.json)
|
321 |
-
* `Hyper-SDXL-1step-unet.safetensors`:
|
|
|
|
|
|
|
322 |
|
323 |
## Citation
|
324 |
```bibtex
|
|
|
18 |
|
19 |
## News🔥🔥🔥
|
20 |
|
21 |
+
* Apr.24, 2024. The ComfyUI [workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SDXL-1step-Unet-workflow.json) and [checkpoint](https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SDXL-1step-Unet-Comfyui.fp16.safetensors) on 1-Step SDXL UNet ✨ is also available! Don't forget ⭕️ to install the custom [scheduler](https://huggingface.co/ByteDance/Hyper-SD/tree/main/comfyui/ComfyUI-HyperSDXL1StepUnetScheduler) in your `ComfyUI/custom_nodes` folder!!!
|
22 |
+
* Apr.23, 2024. ComfyUI workflows on N-Steps LoRAs are [released](https://huggingface.co/ByteDance/Hyper-SD/tree/main/comfyui)! Worth a try for creators 💥!
|
23 |
* Apr.23, 2024. Our technical report 📚 is uploaded to [arXiv](https://arxiv.org/abs/2404.13686)! Many implementation details are provided and we welcome more discussions👏.
|
24 |
+
* Apr.21, 2024. Hyper-SD ⚡️ is highly compatible and work well with different base models and controlnets. To clarify, we also append the usage example of controlnet [here](https://huggingface.co/ByteDance/Hyper-SD#controlnet-usage).
|
25 |
+
* Apr.20, 2024. Our checkpoints and two demos 🤗 (i.e. [SD15-Scribble](https://huggingface.co/spaces/ByteDance/Hyper-SD15-Scribble) and [SDXL-T2I](https://huggingface.co/spaces/ByteDance/Hyper-SDXL-1Step-T2I)) are publicly available on [HuggingFace Repo](https://huggingface.co/ByteDance/Hyper-SD).
|
26 |
|
27 |
## Try our Hugging Face demos:
|
28 |
Hyper-SD Scribble demo host on [🤗 scribble](https://huggingface.co/spaces/ByteDance/Hyper-SD15-Scribble)
|
|
|
317 |
image.save('image_out.png')
|
318 |
```
|
319 |
## Comfyui Usage
|
320 |
+
* `Hyper-SDXL-Nstep-lora.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SDXL-Nsteps-lora-workflow.json)
|
321 |
* `Hyper-SD15-Nstep-lora.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SD15-Nsteps-lora-workflow.json)
|
322 |
+
* `Hyper-SDXL-1step-unet.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SDXL-1step-Unet-workflow.json)
|
323 |
+
* **REQUIREMENT / INSTALL** for 1-Step SDXL UNet: Please install our [scheduler folder](https://huggingface.co/ByteDance/Hyper-SD/tree/main/comfyui/ComfyUI-HyperSDXL1StepUnetScheduler) into your `ComfyUI/custom_nodes` to enable sampling from 800 timestep instead of 999.
|
324 |
+
* i.e. making sure the `ComfyUI/custom_nodes/ComfyUI-HyperSDXL1StepUnetScheduler` folder exist.
|
325 |
+
* For more details, please refer to our [technical report](https://arxiv.org/abs/2404.13686).
|
326 |
|
327 |
## Citation
|
328 |
```bibtex
|