Qwen Voice Clone + LTX 2.3 Image and Speech to Video. Made Locally on RTX3090
Discussion and practical takeaways on Qwen Voice Clone + LTX 2.3 Image and Speech to Video. Made Locally on RTX3090 for LTX-2.x creators.
This thread covers Qwen Voice Clone + LTX 2.3 Image and Speech to Video. Made Locally on RTX3090 and surfaces practical community feedback on LTX-2.x behavior, quality, or workflow tradeoffs in real-world runs.
Reference links:
- https://www.youtube.com/shorts/fAHuY7JPgfU
- https://github.com/1038lab/ComfyUI-QwenTTS/blob/main/example\_workflows/QwenTTS.json
- https://github.com/1038lab/ComfyUI-QwenTTS/blob/main/example_workflows/QwenTTS.json
- https://huggingface.co/datasets/Yogesh-DevHub/LTX2.3/resolve/main/Two-Stage-T2V-%26-I2V-GGUF/Ltx2\_3\_i2v\_GGUF.json
- https://huggingface.co/datasets/Yogesh-DevHub/LTX2.3/resolve/main/Two-Stage-T2V-%26-I2V-GGUF/Ltx2_3_i2v_GGUF.json