V3 support for many tasks as possible in Huggingface, starting with "text-to-image"

With V2, the `HuggingFace` class allowed to do inference on many different models performing different tasks. Moving to V3 many of the available tasks are not functional anymore.

I would like to see them working again with the V3 `ModelBuilder` interface, and to be able to use a short code snippet to deploy a model.
Here's the complete list of the tasks we used to support:
```
"text-classification",
"token-classification",
"table-question-answering",
"question-answering",
"zero-shot-classification",
"translation",
"summarization",
"feature-extraction",
"text-generation",
"fill-mask",
"sentence-similarity",
"automatic-speech-recognition",
"text-to-image",
"text-to-speech",
"audio-to-audio",
"audio-classification",
"image-classification",
"object-detection",
"image-segmentation"
```

The most important tasks for us are "text-generation" (already working on V3) and "text-to-image" (currently broken). If you think you can make at least these two work it would be great.

An example of model that we would like to test is **black-forest-labs/FLUX.2-dev**.

未指定任何文件或测试。首先阅读已经支持 text-generation 的 V3 ModelBuilder 路径，然后研究如何部署所提供的 FLUX.2-dev 模型以实现 text-to-image。完成标准是至少让 text-generation 和 text-to-image 通过 V3 运行，并附带一段简短的部署代码片段，同时在可能的情况下处理对所列任务的更广泛支持。

由索引模型根据 Issue 内容生成。