Instructions to use Chroma111/CivitAI-Archive-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Chroma111/CivitAI-Archive-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Chroma111/CivitAI-Archive-2", 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
Upload 757255/846741/README.md with huggingface_hub
Browse files- 757255/846741/README.md +62 -4
757255/846741/README.md
CHANGED
|
@@ -1,11 +1,69 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
license: other
|
| 4 |
tags:
|
| 5 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
|
|
|
| 7 |
Author: [Abzaloff](https://civitai.com/user/Abzaloff)
|
| 8 |
|
| 9 |
-
Model: [
|
|
|
|
|
|
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
+
- base model
|
| 5 |
+
- fantasy
|
| 6 |
+
- flux1.d
|
| 7 |
+
- nf4
|
| 8 |
+
- photorealistic
|
| 9 |
+
- realistic
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Precise Flux dev NF4 FP8/FP16 | CLIP and VAE included - v1.0 fp16 - 846741
|
| 13 |
+
|
| 14 |
+
**Model Type**: Checkpoint
|
| 15 |
+
|
| 16 |
+
**Base Model**: Flux.1 D
|
| 17 |
+
|
| 18 |
+
**Trigger Words**: None
|
| 19 |
+
|
| 20 |
+
**Tags**: base model, fantasy, flux1.d, nf4, photorealistic, realistic
|
| 21 |
+
|
| 22 |
+
## Gallery
|
| 23 |
+
|
| 24 |
+
<table>
|
| 25 |
+
<tr>
|
| 26 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/79455b51-e9f9-4e30-b8ca-a86cea18cb4d/original=true/31781265.jpeg" width="200"></td>
|
| 27 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6ba6399f-e868-4d56-a37f-13b830cec9bc/original=true/29538180.jpeg" width="200"></td>
|
| 28 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/dd1af8ce-2fe4-4be9-b790-4c37fb6ccdf5/original=true/29538167.jpeg" width="200"></td>
|
| 29 |
+
</tr>
|
| 30 |
+
<tr>
|
| 31 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ea9a06e9-4777-4dfe-bb87-62d48d20845b/original=true/29538169.jpeg" width="200"></td>
|
| 32 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/79124ed9-aa8c-4d8f-a082-9f73d4c2050c/original=true/29538166.jpeg" width="200"></td>
|
| 33 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/48d51fd3-4f4d-4584-80fe-c7ed27aeca24/original=true/29538172.jpeg" width="200"></td>
|
| 34 |
+
</tr>
|
| 35 |
+
<tr>
|
| 36 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b41f7082-6b75-4ce8-809f-5378d15e46b1/original=true/29538171.jpeg" width="200"></td>
|
| 37 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b1702d60-ae4a-4cb9-9733-537789e17855/original=true/29538186.jpeg" width="200"></td>
|
| 38 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/13293d25-0828-409d-a271-f03d2b3ddbcd/original=true/29538174.jpeg" width="200"></td>
|
| 39 |
+
</tr>
|
| 40 |
+
<tr>
|
| 41 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8b744a76-f060-4423-8f20-46d6cf6ba9b3/original=true/29538176.jpeg" width="200"></td>
|
| 42 |
+
</tr>
|
| 43 |
+
</table>
|
| 44 |
+
|
| 45 |
+
## Description
|
| 46 |
+
|
| 47 |
+
### This model is converted to bnb nf4 by mixing Flux dev fp8 with VAE, text encoder T5xxl-fp8 and Clip-l. All included!
|
| 48 |
+
|
| 49 |
+
For those who don't care about size, also blended full dev fp16 with VAE, text encoder T5xxl-fp16 and Clip-l in NF4. All included!
|
| 50 |
+
|
| 51 |
+
From many observations, the FP8 is a bit more accurate in understanding the prompt. And having assembled this build and tested it, I came to the same conclusion.
|
| 52 |
+
|
| 53 |
+
This model is a bit more accurate than the familiar NF4 v2. I've done a lot of generation with complex prompts to assert this. And I am completely satisfied with the way this model understands me. With simple prompts I didn't notice any difference.
|
| 54 |
+
|
| 55 |
+
The model works well with lors in Forge, in which I create in. Don't forget to select in Diffusion in Low Bits: Automatic (fp16 LoRA).
|
| 56 |
+
|
| 57 |
+
In Forge I choose Euler or Flux Realistic samplers, Schedule type: Simple. CFG: 1, number of steps 20-30.
|
| 58 |
+
|
| 59 |
+
Generated outputs can be used for personal, scientific, and commercial purposes as described in the [**flux-1-dev-non-commercial-license**](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)
|
| 60 |
+
|
| 61 |
---
|
| 62 |
+
|
| 63 |
Author: [Abzaloff](https://civitai.com/user/Abzaloff)
|
| 64 |
|
| 65 |
+
Model: [CivitAI Model Page](https://civitai.com/models/757255?modelVersionId=846741)
|
| 66 |
+
|
| 67 |
+
Archive: [CivArchive Page](https://civarchive.com/models/757255?modelVersionId=846741)
|
| 68 |
|
| 69 |
+
<!-- Version: 20260426_upload -->
|