Upload Qwen-Image_V1/README.md with huggingface_hub
Browse files- Qwen-Image_V1/README.md +76 -0
Qwen-Image_V1/README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- art
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Tsunade
|
| 9 |
+
|
| 10 |
+
**Creator**: [SamLiu](https://civitai.com/user/SamLiu)
|
| 11 |
+
**Type**: LORA
|
| 12 |
+
**Base Model**: Qwen
|
| 13 |
+
**Version**: Qwen-Image_V1
|
| 14 |
+
**Trigger Words**: `N/A`
|
| 15 |
+
|
| 16 |
+
**Civitai Model ID**: 356069
|
| 17 |
+
**Civitai Version ID**: 2132756
|
| 18 |
+
|
| 19 |
+
**Stats (at time of fetch for this version)**:
|
| 20 |
+
* Downloads: 98
|
| 21 |
+
* Rating: 0 (0 ratings)
|
| 22 |
+
* Favorites: N/A
|
| 23 |
+
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
## 📄 Description (Parent Model)
|
| 27 |
+
|
| 28 |
+
Qwen-image:
|
| 29 |
+
Qwen-image is really good at anime and 3D
|
| 30 |
+
! It won't be long before someone starts fine-tuning it, possibly
|
| 31 |
+
in a month, two months, and we might see some super amazing NSFW checkpoints popping up.
|
| 32 |
+
It can be precise and true to the original character.
|
| 33 |
+
Good results can be achieved with minimal training—it’s easy to train.
|
| 34 |
+
It far surpasses models like SDXL, Flux, and Wan in terms of anatomy, image quality, text generation, and the resolution of generated images.
|
| 35 |
+
Wan2.1_T2V_14B_V1:
|
| 36 |
+
etc.
|
| 37 |
+
Hunyuan_V1:
|
| 38 |
+
I
|
| 39 |
+
rarely use high resolution when generating with HunyuanVideo. It's not like the Lora quality is bad – it's more that cranking up the resolution eats up way too much time and gets expensive fast. If that's not a concern for you, though, go ahead and try running these Lora at 720P resolution. No doubt, the results will be even better.
|
| 40 |
+
NoobAI(ill)
|
| 41 |
+
V-Pred
|
| 42 |
+
:
|
| 43 |
+
It's basically just the same old training dataset anyway, all for the sake of Rule34.
|
| 44 |
+
Notes:
|
| 45 |
+
This model requires V-Pred support. SwarmUI and Comfy are recommended.
|
| 46 |
+
It's best to include 'blacked-out region', 'Masked Area', and tags in your negative prompts.
|
| 47 |
+
I thought I had already gotten rid of SDXL, but the community and the sheer power of porn are just too strong, relentlessly breathing life into SDXL. Damn it, I really wish there were a better alternative.
|
| 48 |
+
Checkpoint: https://civitai.com/models/833294/noobai-xl-nai-xl
|
| 49 |
+
Flux-V1:
|
| 50 |
+
Cut some parts
|
| 51 |
+
Clothing: Only keep the green jacket and gray short-sleeved shirt,
|
| 52 |
+
Face shape: middle-aged face, young face,
|
| 53 |
+
Hairstyle: double braids, single ponytail
|
| 54 |
+
Pony-V1
|
| 55 |
+
Key promprt:
|
| 56 |
+
tsunade,Hokage’s hat
|
| 57 |
+
tsunade's Default Dressing \(clothes\),
|
| 58 |
+
White crop top,red skirt,fishnet,
|
| 59 |
+
tsunade's blue jacket \(clothes\),
|
| 60 |
+
tsunade's green Jacket \(clothes\),
|
| 61 |
+
tsunade's sandals \(sandals\),
|
| 62 |
+
|
| 63 |
+
## Civitai Links
|
| 64 |
+
|
| 65 |
+
* **[🔗 View This Version on Civitai →](https://civitai.com/models/356069?modelVersionId=2132756)**
|
| 66 |
+
* [View Full Model Page →](https://civitai.com/models/356069)
|
| 67 |
+
* [View Creator Profile →](https://civitai.com/user/SamLiu)
|
| 68 |
+
|
| 69 |
+
---
|
| 70 |
+
|
| 71 |
+
## File Information
|
| 72 |
+
|
| 73 |
+
* **Filename**: `Tsunade_Qwen_V1-07.safetensors`
|
| 74 |
+
* **Size**: 562.72 MB
|
| 75 |
+
* **Hash (AutoV2)**: `5FE6A3F8D6`
|
| 76 |
+
* **Hash (SHA256)**: `5FE6A3F8D61F49AB991A5E0C05E97BF13278B5A2380562C6CBE69ABD99AC7E5D`
|