|
Download README.md from HJGO/stitchvm: direct link, hf CLI and curl.
- Browser
- Download file 1.61 kB
-
https://huggingface.co/HJGO/stitchvm/resolve/main/README.md
- Command line
-
hf download hf://HJGO/stitchvm/README.md
-
curl -L -o README.md https://huggingface.co/HJGO/stitchvm/resolve/main/README.md
1.61 kB
StitchVM checkpoints
Pretrained StitchVM value-model checkpoints. See the code and model tables for the original twelve SD3.5 / FLUX combinations.
HPSv3 and UnifiedReward-2.0 Qwen3.5
Epoch-5 EMA checkpoints with SD3.5 Medium. Each folder contains the trained adapter and vision suffix, metadata, license notices, and SHA-256 checksums. The upstream diffusion and reward models are required separately.
| Reward model | DiT → Encoder | Checkpoint | Details |
|---|---|---|---|
| HPSv3 | 5 → 2 | Download | Model card |
| UnifiedReward-2.0 Qwen3.5 27B | 3 → 2 | Download | Model card |
| UnifiedReward-2.0 Qwen3.5 4B | 4 → 2 | Download | Model card |
| UnifiedReward-2.0 Qwen3.5 9B | 3 → 2 | Download | Model card |
Training, inference, and evaluation code is available in StitchVM. Start with the shared inference examples, which support all 16 released model combinations and download the matching EMA checkpoint automatically.