README.md

---
base_model:
- THUDM/CogView4-6B
datasets:
- multimodalart/1920-raider-waite-tarot-public-domain
library_name: diffusers
license: other
license_link: https://huggingface.co/THUDM/CogView4-6B/blob/main/LICENSE
widget:
- text: >-
    TRTCRD a trtcrd of a knight mounting a running horse wearing an armor and holding a staff, \"knight of wands\"
  output:
    url: final-5000-0-2-TRTCRD-a-trtcrd-of-a-knig-1741262717.173147.png
- text: >-
    TRTCRD a trtcrd of a woman sitting on a throne, wearing a crown and holding a trophee, \"queen of cups\"
  output:
    url: final-5000-1-2-TRTCRD-a-trtcrd-of-a-woma-1741262717.2762468.png
- text: >-
    TRTCRD a trtcrd of a person in a red robe holding a scale and giving coins to two kneeling figures, surrounded by six pentacles
  output:
    url: final-5000-1-2-TRTCRD-a-trtcrd-of-a-pers-1741262755.184284.png
tags:
- text-to-image
- diffusers-training
- diffusers
- template:sd-lora
- cogview4
---

<Gallery />

This is a LoRA fine-tune of the [THUDM/CogView4-6B](https://huggingface.co/THUDM/CogView4-6B) model.

Code: https://github.com/a-r-r-o-w/finetrainers

Inference code:

```python
import torch
from diffusers import CogView4Pipeline
from diffusers.utils import export_to_video

pipe = CogView4Pipeline.from_pretrained(
    "THUDM/CogView4-6B", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("finetrainers/CogView4-6B-rider-waite-tarot-v0-shifted-sigmas", adapter_name="cogview4-lora")
pipe.set_adapters(["cogview4-lora"], [0.9])

image = pipe("<my-awesome-prompt>").images[0]
image.save("output.png")
```

Training logs are available on WandB [here](https://wandb.ai/aryanvs/finetrainers-cogview4).

NOTE: this checkpoint uses shifted_sigmas logit_normal weighting. For sigmas logit_normal weighting, check https://huggingface.co/finetrainers/CogView4-6B-rider-waite-tarot-v0