Downloads · 30 days
2.9K
32% of all-time downloads
darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-GGUF
Qwen-Image-2.1-PE-T2I-Heretic-GGUF is a text generation model from darrellbest. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as other.
GGUF builds of darrellbest/Qwen-Image-2.1-PE-T2I-Heretic, the refusal-ablated text-to-image prompt rewriter: it turns a short request into a detailed prompt plus a recommended aspect ratio. For llama.cpp and Ollama, i…
Downloads · 30 days
2.9K
32% of all-time downloads
All-time downloads
9.1K
Public
Repo size
33.1 GB
Likes
3
Public
Click a slice to open those files.
.gguf33.1 GB · 100%
From the Hugging Face model README
GGUF builds of darrellbest/Qwen-Image-2.1-PE-T2I-Heretic, the refusal-ablated text-to-image prompt rewriter: it turns a short request into a detailed prompt plus a recommended aspect ratio. For llama.cpp and Ollama, including machines with no CUDA GPU and ARM machines such as the DGX Spark.
Not affiliated with or endorsed by Alibaba / Qwen. Derived from
Qwen/Qwen-Image-2.1-PE-T2Iunder the Qwen Research License (copy included). Non-commercial use only.
system_prompt.txt is included and required. It defines the output contract, and the model is useless without it.
| File | Size | Notes |
|---|---|---|
Qwen-Image-2.1-PE-T2I-Heretic-BF16.gguf | 17.9 GB | Full precision, same weights as the safetensors release. |
Qwen-Image-2.1-PE-T2I-Heretic-Q8_0.gguf | 9.5 GB | Recommended. Near-lossless. |
Qwen-Image-2.1-PE-T2I-Heretic-Q4_K_M.gguf | 5.6 GB | Smallest; some quality loss. |
# Modelfile
FROM ./Qwen-Image-2.1-PE-T2I-Heretic-Q8_0.gguf
SYSTEM """<paste the contents of system_prompt.txt>"""
ollama create pe-t2i-heretic -f Modelfile
ollama run pe-t2i-heretic "a cozy cabin in a snowy forest at dusk"
Ollama packs the file into a single model, so nothing extra is needed at run time.
llama-cli -m Qwen-Image-2.1-PE-T2I-Heretic-Q8_0.gguf \
--system-prompt-file system_prompt.txt
convert_hf_to_gguf.py from llama.cpp (bd4f514), then llama-quantize. Converting this architecture needed a
one-line fix: the Qwen converter reads mtp_num_hidden_layers with a default, but these checkpoints set it to
null, so it has to be coerced to 0 (other converters in llama.cpp already do this with or 0).
Checked after conversion: the Q8_0 build was imported into Ollama and run on a real image, and it described the picture correctly and produced a valid rewrite.
Same prompt, greedy decoding (temperature 0), one RTX PRO 6000 via Ollama. Every build produced a valid rewrite and chose the same 3:2 aspect ratio; the wording differs, as it would between any two runs.
| Build | Speed | Valid rewrite | Aspect ratio | Rewrite length |
|---|---|---|---|---|
| BF16 | 56 tok/s | yes | 3:2 | 472 words |
| Q8_0 | 67 tok/s | yes | 3:2 | 429 words |
| Q4_K_M | 109 tok/s | yes | 3:2 | 364 words |
Q8_0 is the safe default; Q4_K_M is the fastest and stayed coherent here, but it is the one to check on your own prompts.
See the parent card for the measured refusal rates and the damage (KL divergence) they cost.
| Model | Format | Use it with |
|---|---|---|
| PE-T2I-Heretic | bf16 safetensors | transformers / diffusers |
| PE-T2I-Heretic-GGUF | GGUF BF16 / Q8_0 / Q4_K_M | llama.cpp, Ollama |
| PE-T2I-Heretic-NVFP4 | NVFP4 (compressed-tensors) | vLLM on Blackwell |
| PE-I2I-Heretic | bf16 safetensors | transformers / diffusers |
| PE-I2I-Heretic-GGUF | GGUF BF16 / Q8_0 / Q4_K_M (+ mmproj) | llama.cpp, Ollama |
| PE-I2I-Heretic-NVFP4 | NVFP4 (compressed-tensors) | vLLM on Blackwell |
T2I rewrites a short request into a detailed prompt for new images; I2I rewrites an edit instruction, reading the image being edited. Both are prompt rewriters for Qwen-Image-2.1, not image generators.