-
Thanks for the nice work.
> where * is the placeholder string used during inversion. Several model files can be downloaded from [Google drive](https://drive.google.com/file/d/1HcALhFpWexlfrQMgooBui…
-
Does anyone know how to prompt data generation? I would need specific sentence structures.
I tried to reconfigure the prompt itself, but it did not change the generated data sentence by sentence. Do…
-
Thank you for making code publicly available.
Here are the fix in the code for multi-prompt video generation:
1. Add the following line in the argparse section
parser.add_argument("--multipro…
-
I am writing to inquire about the parameters and prompts used in Table 3. Could you kindly share the configurations and prompts you applied for open-ended generation across each model?
-
### System Info
- `transformers` version: 4.44.0
- Platform: Linux-6.9.12-201.fsync.fc40.x86_64-x86_64-with-glibc2.35
- Python version: 3.12.4
- Huggingface_hub version: 0.24.5
- Safetensors vers…
-
I tried setting up a system prompt, but the generated results were unsatisfactory.
I'm wondering if there's something missing in my code settings.
this is my code :
```python
from airllm import …
-
### Feature request / 功能建议
I'm trying to add `latents`
```
latents (torch.FloatTensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for …
-
Here is my result:
![image](https://github.com/user-attachments/assets/8926ce7f-17a0-490c-9ef2-912c59bbdb67)
and my code:
```
import typing as t
import asyncio
from typing import List
from …
-
### System Info
### what i want
So I want a solution that can quickly generate AI output by efficiently using precompute kv caches of text and images of all previous prompts!
### by using…
-
Hi Matteo,
Right now your wonderful FluxSamplerParams+ node is not generating new seeds/generations if nothing chanegs between Queued generations.
Say:
--Prompt is the same and all other sett…