kevinwang676's picture
Upload folder using huggingface_hub
fb4fac3 verified

A newer version of the Gradio SDK is available: 5.9.1

Upgrade

Image Synthesis

Image synthesis is the base feature of DiffSynth Studio. We can generate images with very high resolution.

Example: Stable Diffusion

Example script: sd_text_to_image.py

512*512 1024*1024 2048*2048 4096*4096
512 1024 2048 4096

Example: Stable Diffusion XL

Example script: sdxl_text_to_image.py

1024*1024 2048*2048
1024 2048

Example: Stable Diffusion 3

Example script: sd3_text_to_image.py

LoRA Training: ../train/stable_diffusion_3/

1024*1024 2048*2048
image_1024 image_2048

Example: Kolors

Example script: kolors_text_to_image.py

LoRA Training: ../train/kolors/

1024*1024 2048*2048
image_1024 image_2048

Example: Hunyuan-DiT

Example script: hunyuan_dit_text_to_image.py

LoRA Training: ../train/hunyuan_dit/

1024*1024 2048*2048
image_1024 image_2048

Example: Stable Diffusion XL Turbo

Example script: sdxl_turbo.py

We highly recommend you to use this model in the WebUI.

"black car" "red car"
black_car black_car_to_red_car

Example: Prompt Processing

If you are not native English user, we provide translation service for you. Our prompter can translate other language to English and refine it using "BeautifulPrompt" models. Please see sd_prompt_refining.py for more details.

Prompt: "一个漂亮的女孩". The translation model will translate it to English.

seed=0 seed=1 seed=2 seed=3
0_ 1_ 2_ 3_

Prompt: "一个漂亮的女孩". The translation model will translate it to English. Then the refining model will refine the translated prompt for better visual quality.

seed=0 seed=1 seed=2 seed=3
0 1 2 3

Example: Stable Diffusion 3 with Textual Inversions (Experimental)

Since Stable Diffusion 3 utilizes the same text encoder as Stable Diffusion 1.x, it supports the textual inversions designed for Stable Diffusion 1.x. However, we found that the textual inversions may cause unpredictable effects to the model. We can only guarantee that these textual inversions can be loaded into the model. The example script is sd3_text_to_image_textual_inversion.py

Prompt: "a girl, highly detailed, absurd res, perfect image". Without any textual inversions.

seed=0 seed=1 seed=2 seed=3
image_without_textual_inversion_0 image_without_textual_inversion_1 image_without_textual_inversion_2 image_without_textual_inversion_3

Prompt: "a girl, highly detailed, absurd res, perfect image". With verybadimagenegative_v1.3 on the negative side.

seed=0 seed=1 seed=2 seed=3
image_with_textual_inversion_0 image_with_textual_inversion_1 image_with_textual_inversion_2 image_with_textual_inversion_3