Sana
                                
                                
                                
                                    Sana copied to clipboard
                            
                            
                            
                        SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
The model demonstrates several impressive qualities, and these could be further highlighted by making certain features more accessible. For example, adding an option to run LoRAs directly on Replicate would...
Since `SanaPipline` has been added to Diffusers as a custom pipeline it is possible to use `SanaPipeline` from diffusers. But when trying to use `AutoPipelineForText2Image` which automatically selects the needed...
I want to generate 10 images per prompt But seems out of memory and only use 1 GPU on my server. image = pipe( prompt=prompt_list[0], guidance_scale=5.0, pag_scale=2.0, num_inference_steps=20, num_images_per_prompt=10, generator=torch.Generator(device="cuda").manual_seed(42),...
Can this model store some context information? For example, i want to generate a series of pictures with the same theme. Like generate different pictures with two same character but...
I download the Sana_600M_512px model in /checkpoint, and download the whole Sana_600M_512px_diffusers in /models/diffusers and copy the vae from /Sana_600M_512px_diffusers/vae to models/vae but it repots error Error(s) in loading state_dict...
pipe = SanaPipeline.from_pretrained( "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", variant="bf16", torch_dtype=torch.bfloat16, ) I encountered an error when loading the model with the code above:OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found...
we are finished 1st finetuning https://huggingface.co/AI-Art-Collab/sana-1.6-v10 before/after https://imgsli.com/MzI0NTYy train budget ~50$
Hey, Is their anyway I can use Sana for in-painting task? Thank you.
Firstly, thank you for this model, it's the fastest and highest-quality one I know! I successfully trained a LoRA and sampled it during training. However, when I tried to load...
## SANA: Ultra HD Fast Text to Image Model from NVIDIA Step by Step Tutorial on Windows, Cloud & Kaggle ## YouTube Link : https://youtu.be/KW-MHmoNcqo ### YouTube 4K Tutorial :...