theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-21 08:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix

Browse Source
This commit is contained in:
co63oc
2025-02-26 14:18:36 +08:00
parent bed770248b
commit 4268f5466b
9 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/Ip-Adapter/README.md
View File

@@ -16,14 +16,14 @@ The IP-Adapter model based on Stable Diffusion XL is more powerful. You have the
* Content controlling (original usage of IP-Adapter)
|First, we generate a rabbit.|Next, enable IP-Adapter and let the rabbit jump.|For comparision, disable IP-Adapter to see the generated image.|
|First, we generate a rabbit.|Next, enable IP-Adapter and let the rabbit jump.|For comparison, disable IP-Adapter to see the generated image.|
|-|-|-|
|![rabbit](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/4b452634-ec57-414f-897a-f8c50c74a650)|![rabbit_to_jumping_rabbit](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/b93c5495-0b77-4d97-bcd3-3942858288f2)|![rabbit_to_jumping_rabbit_without_ipa](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/52f37195-65b3-4a38-8d9b-73df37311c15)|
* Style controlling (InstantStyle)
|First, we generate a rabbit.|Next, enable InstantStyle and convert the rabbit to a cat.|For comparision, disable IP-Adapter to see the generated image.|
|First, we generate a rabbit.|Next, enable InstantStyle and convert the rabbit to a cat.|For comparison, disable IP-Adapter to see the generated image.|
|-|-|-|
|![rabbit](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/4b452634-ec57-414f-897a-f8c50c74a650)|![rabbit_to_cat](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/a006b281-f643-4ea9-b0da-712289c96059)|![rabbit_to_cat_without_ipa](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/189bd11e-7a10-4c09-8554-0eebde9150fd)|

4
examples/train/README.md
View File

@@ -45,7 +45,7 @@ file_name,text
04.jpg,a dog
```
Note that if the model is Chinese model (for example, Hunyuan-DiT and Kolors), we recommand to use Chinese texts in the dataset. For example
Note that if the model is Chinese model (for example, Hunyuan-DiT and Kolors), we recommend to use Chinese texts in the dataset. For example
```
file_name,text
@@ -526,7 +526,7 @@ models/stable_diffusion_xl
└── sd_xl_base_1.0.safetensors
```
We observed that Stable Diffusion XL is not float16-safe, thus we recommand users to use float32.
We observed that Stable Diffusion XL is not float16-safe, thus we recommend users to use float32.
```
CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion_xl/train_sdxl_lora.py \

2
examples/train/stable_diffusion_3/train_sd3_lora.py
View File

@@ -41,7 +41,7 @@ def parse_args():
type=str,
default=None,
required=True,
help="Path to pretrained models, seperated by comma. For example, SD3: `models/stable_diffusion_3/sd3_medium_incl_clips_t5xxlfp16.safetensors`, SD3.5-large: `models/stable_diffusion_3/text_encoders/clip_g.safetensors,models/stable_diffusion_3/text_encoders/clip_l.safetensors,models/stable_diffusion_3/text_encoders/t5xxl_fp16.safetensors,models/stable_diffusion_3/sd3.5_large.safetensors`",
help="Path to pretrained models, separated by comma. For example, SD3: `models/stable_diffusion_3/sd3_medium_incl_clips_t5xxlfp16.safetensors`, SD3.5-large: `models/stable_diffusion_3/text_encoders/clip_g.safetensors,models/stable_diffusion_3/text_encoders/clip_l.safetensors,models/stable_diffusion_3/text_encoders/t5xxl_fp16.safetensors,models/stable_diffusion_3/sd3.5_large.safetensors`",
)
parser.add_argument(
"--lora_target_modules",