Instructions to use wikeeyang/Magic-Wan-T2IV-V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wikeeyang/Magic-Wan-T2IV-V3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wikeeyang/Magic-Wan-T2IV-V3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,11 +19,17 @@ base_model_relation: finetune
|
|
| 19 |
1. 更逼真的实物景致与人像肌肤,更好的提示词遵循能力。(Realistic scenes and skin, better prompt compliance)
|
| 20 |
2. 更好的美学构图与人脸优化,对 NSFW 支持能力更好。(Aesthetic composition and facial optimization, better support for NSFW)
|
| 21 |
3. 文生图与文生视频统一模型,支持较短长度的文生视频能力。(Unified for T2I and T2V, support short-length T2V capabilities)
|
|
|
|
| 22 |
|
| 23 |
本模型依旧为纯净底模,可用于微调或 LoRA 训练,也可叠加各种 Turbo / Distill / NSFW / SFW 的 LoRA 使用。
|
| 24 |
|
| 25 |
Pure base model, suitable for fine-tuning or LoRA training, and can also be combined with various Turbo / Distill / SFW / NSFW LoRAs.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
<p align="center">
|
| 28 |
<img src="V3-Sample.jpg" width="1200"/>
|
| 29 |
<p>
|
|
@@ -31,7 +37,7 @@ Pure base model, suitable for fine-tuning or LoRA training, and can also be comb
|
|
| 31 |
|
| 32 |
基础工作流请参见(Base Workflow):[V3-T2Image-Workflow.json](https://huggingface.co/wikeeyang/Magic-Wan-Image-V3/resolve/main/V3-T2Image-Workflow.json), [V3-T2Video-Workflow.json](https://huggingface.co/wikeeyang/Magic-Wan-Image-V3/resolve/main/V3-T2Video-Workflow.json)
|
| 33 |
|
| 34 |
-
Also on: [Modelscope](https://www.modelscope.cn/models/wikeeyang/Magic-Wan-
|
| 35 |
|
| 36 |
===================================================================================
|
| 37 |
|
|
|
|
| 19 |
1. 更逼真的实物景致与人像肌肤,更好的提示词遵循能力。(Realistic scenes and skin, better prompt compliance)
|
| 20 |
2. 更好的美学构图与人脸优化,对 NSFW 支持能力更好。(Aesthetic composition and facial optimization, better support for NSFW)
|
| 21 |
3. 文生图与文生视频统一模型,支持较短长度的文生视频能力。(Unified for T2I and T2V, support short-length T2V capabilities)
|
| 22 |
+
4. 支持英文及少量中文字体的渲染。(English and a limited of Chinese fonts Rendering)
|
| 23 |
|
| 24 |
本模型依旧为纯净底模,可用于微调或 LoRA 训练,也可叠加各种 Turbo / Distill / NSFW / SFW 的 LoRA 使用。
|
| 25 |
|
| 26 |
Pure base model, suitable for fine-tuning or LoRA training, and can also be combined with various Turbo / Distill / SFW / NSFW LoRAs.
|
| 27 |
|
| 28 |
+
感谢:**@亮亮rayne**,[@GuangyuanSD](https://huggingface.co/GuangyuanSD),[@kanttouchthis](https://huggingface.co/kanttouchthis),[@QuantFunc](https://huggingface.co/QuantFunc) 在本模型调制优化过程中给与技术、构图、美学、量化等方面的指导和支持。
|
| 29 |
+
|
| 30 |
+
感谢:[@T8star-Aix](https://space.bilibili.com/385085361),[@AI-KSK](https://space.bilibili.com/110353151),[@黑鹤001](https://space.bilibili.com/515231056),[@大麦茶看AI](https://space.bilibili.com/310599757),[@joeMultimedia](https://space.bilibili.com/612740284) 等一众大佬对本模型的技术评测、使用介绍、社区推荐及进一步微调提升等方面的建议和支持。
|
| 31 |
+
|
| 32 |
+
|
| 33 |
<p align="center">
|
| 34 |
<img src="V3-Sample.jpg" width="1200"/>
|
| 35 |
<p>
|
|
|
|
| 37 |
|
| 38 |
基础工作流请参见(Base Workflow):[V3-T2Image-Workflow.json](https://huggingface.co/wikeeyang/Magic-Wan-Image-V3/resolve/main/V3-T2Image-Workflow.json), [V3-T2Video-Workflow.json](https://huggingface.co/wikeeyang/Magic-Wan-Image-V3/resolve/main/V3-T2Video-Workflow.json)
|
| 39 |
|
| 40 |
+
Also on: [Modelscope](https://www.modelscope.cn/models/wikeeyang/Magic-Wan-T2IV-V3), [Civitai](https://civitai.com/models/1927692)
|
| 41 |
|
| 42 |
===================================================================================
|
| 43 |
|